library(subselect)
library(glmulti)
## Loading required package: rJava
library(leaps)
##
## Attaching package: 'leaps'
##
## The following object is masked from 'package:subselect':
##
## leaps
library(lattice)
library(gridExtra)
## Loading required package: grid
library(ggplot2)
library(randomForest)
## randomForest 4.6-10
## Type rfNews() to see new features/changes/bug fixes.
library(MASS)
library(RODBC)
ch = odbcConnect('Hyne',uid='sa',pwd="password12")
mypanel = function(x,y,...) {
panel.abline(c(0,1), col='grey70', lty=2)
panel.xyplot(x,y,...)
}
B = sqlQuery(ch, "
select
SWILogNumber,
g.MOE [E.g],
g.Density [den.g],
m.swv [v.d.hitman],
h.[Density_kg/m3] [den.d.lhg],
h.[MOE.cltraw] [E.d.clt],
m.pith,
m.wane,
m.bow,
m.crook,
m.twist,
X_Dens [den.d.chh],
X_Clear [den.d.chh.clear],
X_DynE [E.d.chh.dyn],
X_AvgE [E.d.chh.avg],
X_MOE [E.d.chh.moe],
X_min [chh.grade.min],
X_max [chh.grade.max],
xc, yc
from (
select
flitchId,
max(pith) pith,
max(wane) wane,
avg(swv) swv,
avg(bow) bow,
avg(crook) crook,
avg(twist) twist
from manualMeas group by flitchId
) m
left join CHHBoards c on c.flitchId=m.flitchId
left join HyneDryBoards h on h.flitchId=m.flitchId
left join ecoustic g on m.flitchId=g.flitchId
left join (
select
flitchId,
max(SWILogNumber) SWILogNumber
from
boardEndImages i, barcode_image bi, boardEndBarcodes b
where flitchId is not null and i.id=bi.imageId and bi.barcodeId=b.id group by flitchId
) f on f.flitchId=m.flitchId
left join (
select FlitchID, avg(boardCentroidX_mm) xc, avg(boardCentroidY_mm) yc
from boardEndBarcodes b, boardEndImages i, barcode_image bi
where b.id=bi.barcodeId and i.id=bi.imageId
group by FlitchID
) xy on xy.FlitchID=m.flitchId
")
B$pith_wane = paste(B$pith,B$wane)
B$E.d.hitman = B$v.d^2*B$den.d.chh/1e9
# halve the SWV for ridiculosly fast ecoustic velocities
B$v.g = sqrt(B$E.g*1e9/B$den.g)
B$E.g.corrected = B$E.g
ii=!is.na(B$v.g) & B$v.g>4000
B$E.g.corrected[ii] = (B$v.g[ii]/2)^2*B$den.g[ii]/1e9
B$R = sqrt(B$xc^2 + B$yc^2)
B$chh.grade.min = factor(B$chh.grade.min,
ordered=TRUE,
levels=c('NOGRD','MGP10','MGP12'))
B$chh.grade.max = factor(B$chh.grade.max,
ordered=TRUE,
levels=c('NOGRD','MGP10','MGP12'))
1202 boards. 62 not associated with a SWILogNumber.
Note that only 90x40 boards that were manually measured are included in the board dataset, thus excluding:
L = sqlQuery(ch, "
select
p.*,
s.*,
u.SWV [SWV.untrimmed],
t.SWV [SWV],
t.weight,
3.141592654*4.9/3*(rL*rL+rS*rL+rS*rS) [volume.heart]
from
(select *
from logs
where SWILogNumber is not null
and DateAndTime>'2014-08-31 00:00:00') p
left join (select *
from logs
where SWILogNumber is not null
and DateAndTime<'2014-08-31 00:00:00') s
on s.SWILogNumber=p.SWILogNumber
left join yardTrimmed t
on p.SWILogNumber=t.SWILogNumber
left join yardUntrimmed u
on p.SWILogNumber=u.SWILogNumber
left join (select
l.SWILogNumber,
l.heartwoodDiameter_mm/2000 rL,
s.heartwoodDiameter_mm/2000 rS
from
logends l,
logends s
where
s.SWILogNumber=l.SWILogNumber
and s.logEnd='S'
and l.logEnd='L') h
on h.SWILogNumber=p.SWILogNumber
order by p.SWILogNumber")
summ <- function(x) {
return(list(
avg=mean(x, na.rm=TRUE),
p50=median(x, na.rm=TRUE),
p75=quantile(x, 0.75, na.rm=TRUE)
))
}
board.quality.measures = c('E.d.hitman','bow','crook','twist')
for (i in 1:nrow(L)) {
ii=!is.na(B$SWILogNumber) & B$SWILogNumber==L[i,"SWILogNumber"]
L[i,"nboards"]=sum(ii)
L[i,"nboards.complete"]=nrow(na.omit(B[ii,board.quality.measures]))
L[i,"E.avg"]=mean(B$E.d.clt[ii],na.rm=TRUE)
L[i,"E.avg.dyn"]=mean(B$E.d.hitman[ii],na.rm=TRUE)
L[i,"GPa10"]=sum(!is.na(B$E.d.hitman) & B$E.d.hitman>=10 & ii)/sum(ii)
L[i,"GPa8"]=sum(!is.na(B$E.d.hitman) & B$E.d.hitman>=8 & ii)/sum(ii)
L[i,"GPa6"]=sum(!is.na(B$E.d.hitman) & B$E.d.hitman>=6 & ii)/sum(ii)
L[i,"npith"]=sum(ii & (!is.na(B$pith) & B$pith=='y'))
for (measure in board.quality.measures) {
for (region in c('','inner','outer')) {
iregion = rep(TRUE,nrow(B))
if (region=='inner') {
iregion = B$R<=100
} else if (region=='outer') {
iregion = B$R>100
}
results = summ(B[!is.na(B[,measure])&ii&iregion,measure])
for (result in names(results)) {
if (region=='') {
out <- paste(measure,result,sep="_")
} else {
out <- paste(measure,result,region,sep="_")
}
L[i,out] = results[[result]]
}
}
}
}
# alternate log metrics
M = read.csv('/home/harrinjj/G/Projects/Hyne/USNR/logs.csv')
re = "(?:.*USNR Image Files/)([^/]+)/(?:tri_cam)?(.+)\\.bin"
M$scanner = gsub(re,"\\1",M$binfn,perl=TRUE)
M$seq = as.numeric(gsub(re,"\\2",M$binfn,perl=TRUE))
swi.log.numbers.in.sawing.order = sqlQuery(ch, "select SWILogNumber as l from logs where SWILogNumber is not null and DateAndTime>'2014-08-31' order by DateAndTime")$l
# deal with the 8 non-trial logs that were on the deck
ii = M$scanner%in%c('HSS','ELI')
M$seq[ii] = M$seq[ii] - 8
ii=M$scanner%in%c('ELI','HSS')&M$seq>0
M$SWILogNumber[ii] = swi.log.numbers.in.sawing.order[M$seq[ii]]
M$scanner[M$scanner=='KEEPBINFILES'] = 'ROY'
H = sqlQuery(ch, "select ID, SWILogNumber from logs where SWILogNumber is not null")
HH=c()
HH[H$ID]=H$SWILogNumber
for (ID in unique(M$seq[M$seq>500])) {
if (!is.na(HH[ID])) {
M$SWILogNumber[M$seq==ID] = HH[ID]
}
}
# prefix everything (except SWILogNumber) with "m_"
for (col in names(M)) {
if (col=='SWILogNumber') next
M[,paste("m_",col,sep="")] = M[,col]
M[,col] <- NULL
}
M = M[!is.na(M$SWILogNumber),]
merge.overwrite <- function(X,Y,by=NULL) {
if (is.null(by)) {
by = intersect(names(X),names(Y))
print(by)
}
XY = merge(X,Y,by=by,suffixes=c(".x",".y"),all=TRUE)
#browser()
for (col in setdiff(union(names(X),names(Y)),by)) {
# if col.y exists rename as col and remove col.x (if it exists)
if (paste(col,".y",sep="")%in%colnames(XY)) {
XY[,col] = XY[,paste(col,".y",sep="")]
XY[,paste(col,".x",sep="")] <- NULL
XY[,paste(col,".y",sep="")] <- NULL
}
}
return(XY)
}
L.royT = L # log metrics computed at time of sawing from the TRIMMED ROY binfiles
# (A) replace all the log metric info with metrics recomputed from the UNTRIMMED ROY scanner binfiles
L.royU = merge.overwrite(L,M[M$m_trimstate=='untrimmed'&M$m_scanner=='ROY',],by="SWILogNumber")
# (B) replace all the log metric info with metrics recomputed from the TRIMMED ELI scanner binfiles
L.eliT = merge.overwrite(L,M[M$m_trimstate=='trimmed'&M$m_scanner=='ELI',],by="SWILogNumber")
##########################
#L = L.royT ##############
#L = L.royU ##############
L = L.eliT ####### Best option as complete and homogenous
##########################
# calibre uses 0 to indicate missing
L$velocity[L$velocity==0]=NA
L$velocity.1[L$velocity.1==0]=NA
L$hw.vfrac = L$volume.heart / L$volume
L$density = L$weight / L$volume
L$sweep.prod = L$m_sweep1*L$m_sweep2
L$sweep.prod.1 = L$m_sweep1.1*L$m_sweep2.1
L$E.gradient = L$E.d.hitman_avg_inner/L$E.d.hitman_avg_outer
predictors = c('SWV',
'm_volume','m_led','m_sed',
'm_a0','m_a1','m_a2','m_taper','m_waist',
'm_ovality','m_whorliness',
'm_sweep1','m_sweep2',
'weight','density',
'hw.vfrac',
'sweep.prod')
#log.metrics = setdiff(names(L),c("SWILogNumber","scanner","trimstate","source","seq","fail","origOrient","nslices","dzmax","dzmin","binfn","bindir"))
123 logs. 0 with no missing predictor information.
Grab underbark, heart/sap boundary and pith data digitized from log end imagery.
D = sqlQuery(ch, "
select
flipbookNumber SWILogNumber,
logEnd,
e.type,
x_mm x,
y_mm y
from
LogEndDigitizationPoints p,
LogEndDigitizationEdges e,
LogEndDigitizations d
where
p.digitizationId=d.id
and e.digitizationId=d.id
and e.id=p.edgeID")# and logEnd='large'")
Do the two measures of volume/LED/SED agree?
USNR software writes volume, LED and SED to a database for each log. These are also recomputed from the bin files by ‘logmetrics.py’. Do they match?
Yep, pretty much.
Hitman SWV isn’t available for the last trimmed log (223). Can we use untrimmed hitman swv?
#plot(L$SWV,L$SWV.untrimmed*1000.)
#identify(L$SWV,L$SWV.untrimmed*1000.,L$SWILogNumber)
c=rep('grey70',nrow(L))
c[L$SWILogNumber %in% c(157,183)]='red'
c[L$SWILogNumber %in% c(151)]='blue'
c[L$SWILogNumber %in% c(223)]='green'
tmp=L[,c("velocity","SWV.untrimmed","SWV","velocity.1")]
names(tmp)<-c("calibre.select","hitman.untrm","hitman.trmd","calibre.sawing")
pairs(tmp,col=c,main="Comparison of Log SWV Measures")
As well as log 223, there are three outliers (logs 151,157,183).
Trimmed SWV estimate good for logs 157, 183 (i.e. untrimmed SWV wrong).
Use hitman untrimmed estimate for log 151.
Use hitman untrimmed estimate for log 223.
TODO: re-extract hitman SWV from raw hitman data.
L$SWV[L$SWILogNumber==151] = L$SWV.untrimmed[L$SWILogNumber==151]*1000
L$SWV[L$SWILogNumber==223] = L$SWV.untrimmed[L$SWILogNumber==223]*1000
Is the heartwood volume stuff sane?
xyplot(volume.heart ~ volume, L)
xyplot(density ~ I(volume.heart/volume), L,
xlab="heart:total volume", ylab="green log density",
panel=function(x,y,...) {
print(summary(m<-rlm(y ~ x)))
panel.xyplot(x,y,...)
panel.abline(coef(m), col='red')
})
##
## Call: rlm(formula = y ~ x)
## Residuals:
## Min 1Q Median 3Q Max
## -106.145 -20.656 -1.598 21.762 136.072
##
## Coefficients:
## Value Std. Error t value
## (Intercept) 1065.5776 7.5791 140.5938
## x -557.1970 28.9969 -19.2157
##
## Residual standard error: 32.05 on 121 degrees of freedom
Regression suggests average sapwood density of 1066 kg/m^3, with average heartwood density of 1066-557=509 kg/m^3.
Why are the shape metrics (m_*) missing for 10 logs?
9 of these logs (198,201,208,195,205,148,194,206,207) were the first put through, maybe the logselect software wasn’t running. The 10th is a log that for some reason couldn’t be matched to Royalty scanner Id (or perhaps no bin file matching that Id was available).
TODO: use metrics computed from bin file, perhaps from another scanner?
How different are log metrics computed at selection and processing time (i.e. before and after being trimmed to 4.9m)?
par(mfcol=c(4,4))
log.shape.metrics = c("m_volume","m_led","m_sed","m_taper","m_waist","m_ovality","m_whorliness","m_a0","m_a1","m_a2","m_sweep1","m_sweep2","sweep.prod")
for (m in log.shape.metrics) {
plot(formula(paste(m,"~",m,".1",sep="")),L)
}
For the most part log metrics from the same scanner are similar before and after trimming. Where differences do occur it might be due to:
plot(nboards ~ m_volume, L)
identify(L$m_volume, L$nboards, L$SWILogNumber, cex=0.8)
## integer(0)
Only one board recovered from log 106.
Two logs with abnormally poor recovery: 126, 192. Either these were sawn to non-90x40 products or gluing was poor and labels were lost.
Exclude these logs from further analysis.
#L = L[!L$SWILogNumber%in%c(106,126,192),]
bwplot( factor(SWILogNumber,levels=L$SWILogNumber[order(L$E.avg)],ordered=TRUE) ~ E.d.clt, B)
# and again but with only the best and worst and with individual boards
(worst=L$SWILogNumber[L$E.avg<quantile(L$E.avg,0.1)])
## [1] 101 106 163 168 179 184 187 193 205 207 214 218 221
(best=L$SWILogNumber[L$E.avg>quantile(L$E.avg,0.9)])
## [1] 135 137 140 143 154 159 176 190 200 203 206 213 216
bwplot( factor(SWILogNumber,levels=L$SWILogNumber[order(L$E.avg)],ordered=TRUE) ~ E.d.clt, B,subset=SWILogNumber %in% union(best,worst),
panel=function(...){
panel.bwplot(...)
panel.points(...,col='red')
}, main="Best and Worst 10% of Logs")
The worst (least stiff) boards are similar across all logs. The best (most stiff) boards howver range from <10 GPa to >15GPa.
Are good logs small?
plot(L$m_volume[order(L$E.avg)], xlab="log rank - average board stiffness", ylab="volume")
plot(L$nboards[order(L$E.avg)], xlab="log rank - average board stiffness", ylab="nboards")
Bad logs tend to be both a little smaller and represented by fewer boards, but the effect is not strong.
HyneDry data does not include an explicit log grade.
CHH data does, but only “MGP10” and “MGP12” (and “NOGRD” covers the rest)
summary(B[,c("chh.grade.min","chh.grade.max")])
## chh.grade.min chh.grade.max
## NOGRD:531 NOGRD:248
## MGP10:469 MGP10:741
## MGP12: 96 MGP12:107
## NA's :106 NA's :106
addmargins(table(B$chh.grade.min, B$chh.grade.max))
##
## NOGRD MGP10 MGP12 Sum
## NOGRD 248 283 0 531
## MGP10 0 458 11 469
## MGP12 0 0 96 96
## Sum 248 741 107 1096
It is not clear exactly how the CHH grade values relate to measured MOE. Instead lets look at a psuedo-grade.
Note that ‘GPax’ here denotes boards whose average MOE is x GPa or better, which is not the same as having a MGPx grade.
par(mfcol=c(3,1))
hist(L$GPa6, xlim=c(0,1), breaks=c(0:11)/10)
hist(L$GPa8, xlim=c(0,1), breaks=c(0:11)/10)
hist(L$GPa10, xlim=c(0,1), breaks=c(0:11)/10)
xyplot(jitter(L$GPa8,5)~jitter(L$GPa10,5))
Interesting that the 5 best logs if seeking GPa8 include one log that would be in the lower half if you were looking for GPa10.
par(mfcol=c(3,1))
plot(GPa6~ E.avg.dyn, L)
plot(GPa8~ E.avg.dyn, L)
plot(GPa10~ E.avg.dyn, L)
Log average MOE is not necessarily a good predictor of fraction of boards exceeding a particular MOE limit.
How does the fraction GPa10+ vary with log quality? I.e. what is the % of GPa10+ in the worst X% of logs?
par(mfcol=c(1,1))
F=ecdf(L$GPa6)
plot(F)
quantile(L$GPa6, 0.05)
## 5%
## 0.5038462
quantile(L$GPa6, 0.10)
## 10%
## 0.5866667
TODO: using a model for log stiffness based on pre-sawing measures, redo this.
Does it matter if we use Hitman instead of CLT results?
bwplot( factor(SWILogNumber,levels=L$SWILogNumber[order(L$E.avg.dyn)],ordered=TRUE) ~ E.d.hitman, B)
# and again but with only the best and worst and with individual boards
(worst.dyn=L$SWILogNumber[L$E.avg<quantile(L$E.avg,0.1)])
## [1] 101 106 163 168 179 184 187 193 205 207 214 218 221
(best.dyn=L$SWILogNumber[L$E.avg>quantile(L$E.avg,0.9)])
## [1] 135 137 140 143 154 159 176 190 200 203 206 213 216
bwplot( factor(SWILogNumber,levels=L$SWILogNumber[order(L$E.avg)],ordered=TRUE) ~ E.d.hitman, B,subset=SWILogNumber %in% union(best.dyn,worst.dyn),
panel=function(...){
panel.bwplot(...)
panel.points(...,col='red')
}, main="Best and Worst 10% of logs")
intersect(best, best.dyn)
## [1] 135 137 140 143 154 159 176 190 200 203 206 213 216
intersect(worst, worst.dyn)
## [1] 101 106 163 168 179 184 187 193 205 207 214 218 221
plot(L$E.avg,L$E.avg.dyn)
plot(rank(L$E.avg),rank(L$E.avg.dyn))
No, we get the same sets of logs as best and worst using either hitman+chh.density or clt for board MOE.
From here on use Hitman and CHH density based board and log average MOE.
Do all logs have a similar number of pith-in boards?
plot(L$SWILogNumber, L$nboards, ylim=c(0,max(L$nboards)))
points(L$SWILogNumber, L$npith, col='red')
table(L$npith)
##
## 0 1 2 3 4
## 7 43 59 13 1
L$SWILogNumber[L$npith==0]
## [1] 106 115 125 126 147 175 219
Typically 1 or 2 pith boards per log. BUT 7 logs with no pith boards (either not recovered or not properly classified), this might skew which logs appear to be best and worst. One of these seven is also a worst 10% log so probably not an issue.
Is the fraction of pith boards a good predictor of log average stiffness?
xyplot(E.avg.dyn ~ I(npith/nboards), L)
No.
pairs(B[,c('den.d.chh','den.d.chh.clear','den.d.lhg'),])
CHH clear (X_Clear) and average (X_Dens) densities are pretty similar.
Use the latter (X_Dens) in conjunction with SWV to estimate MOE.
xyplot(den.d.chh ~ den.g, B, group=paste("wane =",wane), auto.key=TRUE)
Most of the incredibly high green density boards are waney. Probably the green mass is good, but the green volume is underestimated.
plot(pith ~ R, B)
Wow. There are pith containing boards whose LE position is 140-160 mm from pith at LE.
mypanel = function(...) {
panel.xyplot(...)
panel.grid(h=-1,v=-1)
panel.loess(..., col='red')
}
grid.arrange(
xyplot(den.g ~ R, B, panel=mypanel, group=wane),
xyplot(den.d.chh ~ R, B, panel=mypanel, group=wane),
xyplot(den.d.lhg ~ R, B, panel=mypanel, group=wane),
ncol=3)
grid.arrange(
xyplot(E.g.corrected ~ R, B, panel=mypanel, group=wane),
xyplot(E.d.chh.dyn ~ R, B, panel=mypanel, group=wane),
xyplot(E.d.hitman ~ R, B, panel=mypanel, group=wane),
ncol=3)
grid.arrange(
xyplot(bow ~ R, B, panel=mypanel, group=wane),
xyplot(crook ~ R, B, panel=mypanel, group=wane),
xyplot(twist ~ R, B, panel=mypanel, group=wane),
ncol=3)
Most of the plots above exhibit a slope discontinuity between \(R=100\) and \(R=150\) mm.
Lets call boards with \(R<100\) ‘inner’ and those with \(R>100\) mm ‘outer’.
Plot variation of moe, den, bow, crook, twist with R within individual logs
for (p in c("den.g","den.d.chh","E.d.chh.dyn","bow","crook","twist")) {
print(
xyplot(formula(paste(p,"~ R | as.factor(SWILogNumber)")), B, group=pith_wane, pch=c(1,19,19,19), main=p)#, auto.key=TRUE)
)
}
Some very odd arrangements of pith and waney boards (e.g log 137 where a pith board has R > than a wane board!)
Todo: plot moe, den, bow, crook, twist using glyph size/color/fill over individual log saw patterns
ii = is.finite(B$SWILogNumber) & is.finite(B$xc) & is.finite(B$yc)
for (p in c("den.g","den.d.chh","E.d.chh.dyn","bow","crook","twist")) {
#B$sf=B[,p]/max(B[,p])
#xyplot(yc ~ xc | as.factor(SWILogNumber), aspect='iso', B, cex=B$sf, pch=19, subset=is.finite(p))#, cex=p)#, auto.key=TRUE)
# try ggplot2
B$size=B[,p]
print(
ggplot(B[is.finite(B$size) & ii,], aes(xc,yc))
+ geom_point(aes(size=sqrt(abs(size)),col=size,alpha=0.9))
+ geom_point(col='black', shape="+")
+ facet_wrap(~SWILogNumber)
+ coord_fixed() # achieves aspect='iso'
+ scale_colour_gradientn(colours=rainbow(4))
+ ggtitle(p)
)
}
Which logs are well represented?
Plot board positions and digitized large end information.
xyplot(y ~ x | as.factor(SWILogNumber), group=paste(logEnd,type), D, type="l", aspect='iso',
panel=function(x,y,subscripts,...){
panel.grid(h=-1,y=-1)
log = D$SWILogNumber[subscripts][1]
ii = B$SWILogNumber==log
panel.xyplot(B$xc[ii],B$yc[ii],pch=19,col='black', cex=0.5)
panel.xyplot(x,y,subscripts=subscripts,...)
})
# and so after much scrutinising...
near.complete.sawpatterns = c(213,217,219,220,221,223,212,210,108,111,125,119,114,128,144,150,154,164,188,186,197)
How is it that some boards fall outside of the large end? e.g. 103. Do I have the rotations correct?
mypanel=function(x,y,...){
#panel.abline(c(0,1), col='grey70', lty=2)
panel.xyplot(x,y,...)
m=lm(y ~ x)
print(summary(m))
panel.abline(coef(m),col='red')
}
#xyplot(E.avg ~ SWV, L, panel=mypanel) # hitman in yard
#xyplot(E.avg ~ velocity, L, subset=velocity>0, panel=mypanel) # calibre log tool
xyplot(E.avg.dyn ~ SWV, L, panel=mypanel) # hitman in yard
##
## Call:
## lm(formula = y ~ x)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.5226 -0.6399 0.0464 0.7224 2.8393
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -4.5446846 1.4600138 -3.113 0.00231 **
## x 0.0041265 0.0004422 9.331 6.33e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.196 on 121 degrees of freedom
## Multiple R-squared: 0.4184, Adjusted R-squared: 0.4136
## F-statistic: 87.06 on 1 and 121 DF, p-value: 6.332e-16
#xyplot(E.avg.dyn ~ velocity, L, subset=velocity>0, panel=mypanel) # calibre log tool
Ugly.
bwpanel=function(...){
panel.bwplot(...)
panel.points(...,col='red', cex=0.3)
}
bwplot( factor(SWILogNumber,levels=L$SWILogNumber[order(L$bow_p75)],ordered=TRUE) ~ bow, B, panel=bwpanel)
bwplot( factor(SWILogNumber,levels=L$SWILogNumber[order(L$crook_p75)],ordered=TRUE) ~ crook, B, panel=bwpanel)
bwplot( factor(SWILogNumber,levels=L$SWILogNumber[order(L$twist_p75)],ordered=TRUE) ~ twist, B, panel=bwpanel)
log.quality.measures = c("E.avg.dyn",
"crook_avg","crook_p75","crook_avg_inner","crook_avg_outer",
"bow_avg","bow_p75","bow_avg_outer","bow_avg_inner",
"twist_avg")
pairs(L[,log.quality.measures],
lower.panel=function(x,y,...) {
usr <- par("usr"); on.exit(par(usr))
par(usr = c(0, 1, 0, 1))
ii=is.finite(x) & is.finite(y)
r <- cor(x[ii], y[ii])
txt <- format(c(r, 0.123456789), digits = 2)[1]
#txt <- paste0("r=", txt)
#cex.cor <- 0.8/strwidth(txt)
text(0.5, 0.5, txt, cex = 1.8 * abs(r))
})
Average and 75th percentile bow and crook strongly correlated. Consider only average from here on.
log.quality.measures = c("E.avg.dyn",
"crook_avg","crook_avg_inner","crook_avg_outer",
"bow_avg","bow_avg_outer","bow_avg_inner",
"twist_avg")
plots <- list()
for (l in log.quality.measures) {
for (p in predictors) {
plots <- c(plots, list(xyplot(L[,l] ~ L[,p], xlab=p, ylab=l)))
}
}
do.call(grid.arrange, c(plots, nrow=length(predictors)))
Twist turns out to be surprisingly predictable (see below). Is this due to correlation with stiffness?
xyplot(E.d.hitman_avg ~ twist_avg, L)
summary(lm(E.d.hitman_avg ~ twist_avg, L))
##
## Call:
## lm(formula = E.d.hitman_avg ~ twist_avg, data = L)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.7408 -0.9521 -0.0143 0.9708 4.0205
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10.09563 0.22422 45.026 < 2e-16 ***
## twist_avg -0.34252 0.06032 -5.679 9.5e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.394 on 121 degrees of freedom
## Multiple R-squared: 0.2104, Adjusted R-squared: 0.2039
## F-statistic: 32.25 on 1 and 121 DF, p-value: 9.503e-08
Find the best linear model for log average MOE.
summary(m <- lm(E.avg.dyn ~ (m_volume+SWV+m_led+m_sed+m_a0+m_a1+m_a2+m_taper+m_waist+m_ovality+m_whorliness+m_sweep1+m_sweep2+weight+hw.vfrac), L, subset=!is.na(L$m_sed)))
##
## Call:
## lm(formula = E.avg.dyn ~ (m_volume + SWV + m_led + m_sed + m_a0 +
## m_a1 + m_a2 + m_taper + m_waist + m_ovality + m_whorliness +
## m_sweep1 + m_sweep2 + weight + hw.vfrac), data = L, subset = !is.na(L$m_sed))
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.4840 -0.4265 -0.0343 0.4913 1.7277
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -4.835e+00 1.958e+00 -2.469 0.0151 *
## m_volume -3.814e+00 5.619e+00 -0.679 0.4988
## SWV 4.965e-03 3.797e-04 13.075 < 2e-16 ***
## m_led 3.753e-02 2.625e-02 1.430 0.1558
## m_sed 9.822e-03 1.422e-02 0.691 0.4913
## m_a0 -5.402e-02 3.274e-02 -1.650 0.1019
## m_a1 1.065e-01 9.377e-02 1.135 0.2587
## m_a2 -2.104e-02 1.017e-01 -0.207 0.8365
## m_taper -6.958e-01 4.518e-01 -1.540 0.1265
## m_waist 1.257e+01 5.238e+00 2.399 0.0181 *
## m_ovality 4.784e+01 1.109e+02 0.431 0.6671
## m_whorliness -6.084e-01 3.334e-01 -1.825 0.0708 .
## m_sweep1 1.814e-01 1.404e-01 1.292 0.1991
## m_sweep2 -1.354e+00 8.082e-01 -1.675 0.0968 .
## weight 7.223e-03 4.573e-03 1.580 0.1171
## hw.vfrac -5.500e+00 1.213e+00 -4.534 1.51e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8278 on 107 degrees of freedom
## Multiple R-squared: 0.7538, Adjusted R-squared: 0.7193
## F-statistic: 21.84 on 15 and 107 DF, p-value: < 2.2e-16
summary(m.best <- step(m, direction="both"))
## Start: AIC=-31.62
## E.avg.dyn ~ (m_volume + SWV + m_led + m_sed + m_a0 + m_a1 + m_a2 +
## m_taper + m_waist + m_ovality + m_whorliness + m_sweep1 +
## m_sweep2 + weight + hw.vfrac)
##
## Df Sum of Sq RSS AIC
## - m_a2 1 0.029 73.355 -33.575
## - m_ovality 1 0.127 73.454 -33.410
## - m_volume 1 0.316 73.642 -33.096
## - m_sed 1 0.327 73.653 -33.077
## - m_a1 1 0.883 74.210 -32.151
## - m_sweep1 1 1.144 74.470 -31.720
## <none> 73.326 -31.624
## - m_led 1 1.400 74.726 -31.297
## - m_taper 1 1.626 74.952 -30.927
## - weight 1 1.710 75.036 -30.789
## - m_a0 1 1.866 75.192 -30.533
## - m_sweep2 1 1.923 75.249 -30.439
## - m_whorliness 1 2.282 75.608 -29.855
## - m_waist 1 3.945 77.271 -27.178
## - hw.vfrac 1 14.089 87.415 -12.006
## - SWV 1 117.154 190.480 83.796
##
## Step: AIC=-33.57
## E.avg.dyn ~ m_volume + SWV + m_led + m_sed + m_a0 + m_a1 + m_taper +
## m_waist + m_ovality + m_whorliness + m_sweep1 + m_sweep2 +
## weight + hw.vfrac
##
## Df Sum of Sq RSS AIC
## - m_ovality 1 0.126 73.482 -35.363
## - m_sed 1 0.365 73.721 -34.964
## - m_volume 1 1.030 74.385 -33.860
## - m_sweep1 1 1.116 74.472 -33.717
## <none> 73.355 -33.575
## - m_led 1 1.413 74.768 -33.228
## - m_a0 1 1.855 75.211 -32.503
## - m_sweep2 1 1.902 75.257 -32.427
## - m_whorliness 1 2.300 75.655 -31.778
## + m_a2 1 0.029 73.326 -31.624
## - weight 1 2.835 76.191 -30.910
## - m_a1 1 3.768 77.124 -29.413
## - m_waist 1 4.457 77.812 -28.320
## - m_taper 1 5.693 79.048 -26.382
## - hw.vfrac 1 15.493 88.849 -12.006
## - SWV 1 117.580 190.936 82.089
##
## Step: AIC=-35.36
## E.avg.dyn ~ m_volume + SWV + m_led + m_sed + m_a0 + m_a1 + m_taper +
## m_waist + m_whorliness + m_sweep1 + m_sweep2 + weight + hw.vfrac
##
## Df Sum of Sq RSS AIC
## - m_sed 1 0.398 73.879 -36.699
## - m_volume 1 1.007 74.489 -35.689
## - m_sweep1 1 1.204 74.685 -35.365
## <none> 73.482 -35.363
## - m_led 1 1.395 74.877 -35.050
## - m_a0 1 1.834 75.315 -34.331
## - m_sweep2 1 2.029 75.511 -34.013
## + m_ovality 1 0.126 73.355 -33.575
## + m_a2 1 0.028 73.454 -33.410
## - m_whorliness 1 2.421 75.903 -33.375
## - weight 1 2.728 76.209 -32.880
## - m_a1 1 3.926 77.408 -30.961
## - m_waist 1 4.618 78.100 -29.866
## - m_taper 1 5.818 79.300 -27.990
## - hw.vfrac 1 15.604 89.086 -13.677
## - SWV 1 117.475 190.957 80.103
##
## Step: AIC=-36.7
## E.avg.dyn ~ m_volume + SWV + m_led + m_a0 + m_a1 + m_taper +
## m_waist + m_whorliness + m_sweep1 + m_sweep2 + weight + hw.vfrac
##
## Df Sum of Sq RSS AIC
## - m_volume 1 1.139 75.018 -36.818
## <none> 73.879 -36.699
## - m_sweep1 1 1.238 75.118 -36.655
## - m_led 1 1.265 75.145 -36.610
## - m_a0 1 1.438 75.318 -36.328
## - m_sweep2 1 1.851 75.730 -35.656
## + m_sed 1 0.398 73.482 -35.363
## + m_ovality 1 0.159 73.721 -34.964
## + m_a2 1 0.068 73.811 -34.813
## - weight 1 3.080 76.959 -33.676
## - m_whorliness 1 3.336 77.215 -33.267
## - m_a1 1 4.134 78.013 -32.002
## - m_waist 1 4.782 78.661 -30.986
## - m_taper 1 5.829 79.709 -29.358
## - hw.vfrac 1 15.211 89.090 -15.672
## - SWV 1 120.037 193.917 79.995
##
## Step: AIC=-36.82
## E.avg.dyn ~ SWV + m_led + m_a0 + m_a1 + m_taper + m_waist + m_whorliness +
## m_sweep1 + m_sweep2 + weight + hw.vfrac
##
## Df Sum of Sq RSS AIC
## <none> 75.018 -36.818
## - m_sweep1 1 1.238 76.257 -36.804
## - m_led 1 1.293 76.311 -36.716
## + m_volume 1 1.139 73.879 -36.699
## + m_a2 1 0.928 74.090 -36.349
## - m_sweep2 1 1.794 76.812 -35.911
## - m_a0 1 1.823 76.842 -35.864
## + m_sed 1 0.529 74.489 -35.689
## - weight 1 1.946 76.964 -35.668
## + m_ovality 1 0.137 74.882 -35.042
## - m_whorliness 1 2.944 77.962 -34.084
## - m_a1 1 3.535 78.553 -33.154
## - m_waist 1 4.188 79.206 -32.136
## - m_taper 1 5.270 80.288 -30.467
## - hw.vfrac 1 23.134 98.152 -5.756
## - SWV 1 121.581 196.599 79.685
##
## Call:
## lm(formula = E.avg.dyn ~ SWV + m_led + m_a0 + m_a1 + m_taper +
## m_waist + m_whorliness + m_sweep1 + m_sweep2 + weight + hw.vfrac,
## data = L, subset = !is.na(L$m_sed))
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.6616 -0.3750 -0.0511 0.5017 1.6243
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -4.3712770 1.7539168 -2.492 0.01417 *
## SWV 0.0050099 0.0003735 13.413 < 2e-16 ***
## m_led 0.0358645 0.0259284 1.383 0.16938
## m_a0 -0.0459245 0.0279586 -1.643 0.10330
## m_a1 0.1162266 0.0508187 2.287 0.02409 *
## m_taper -0.7343405 0.2629693 -2.792 0.00616 **
## m_waist 11.5402313 4.6357006 2.489 0.01428 *
## m_whorliness -0.6522707 0.3125403 -2.087 0.03918 *
## m_sweep1 0.1841004 0.1359972 1.354 0.17858
## m_sweep2 -1.2690052 0.7787996 -1.629 0.10606
## weight 0.0048431 0.0028539 1.697 0.09250 .
## hw.vfrac -5.9220943 1.0122030 -5.851 5.03e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8221 on 111 degrees of freedom
## Multiple R-squared: 0.7481, Adjusted R-squared: 0.7231
## F-statistic: 29.97 on 11 and 111 DF, p-value: < 2.2e-16
m.best$anova
## Step Df Deviance Resid. Df Resid. Dev AIC
## 1 NA NA 107 73.32606 -31.62400
## 2 - m_a2 1 0.02932643 108 73.35538 -33.57482
## 3 - m_ovality 1 0.12634602 109 73.48173 -35.36315
## 4 - m_sed 1 0.39771212 110 73.87944 -36.69922
## 5 - m_volume 1 1.13863463 111 75.01808 -36.81800
m.best <- step(m, direction="backward")
## Start: AIC=-31.62
## E.avg.dyn ~ (m_volume + SWV + m_led + m_sed + m_a0 + m_a1 + m_a2 +
## m_taper + m_waist + m_ovality + m_whorliness + m_sweep1 +
## m_sweep2 + weight + hw.vfrac)
##
## Df Sum of Sq RSS AIC
## - m_a2 1 0.029 73.355 -33.575
## - m_ovality 1 0.127 73.454 -33.410
## - m_volume 1 0.316 73.642 -33.096
## - m_sed 1 0.327 73.653 -33.077
## - m_a1 1 0.883 74.210 -32.151
## - m_sweep1 1 1.144 74.470 -31.720
## <none> 73.326 -31.624
## - m_led 1 1.400 74.726 -31.297
## - m_taper 1 1.626 74.952 -30.927
## - weight 1 1.710 75.036 -30.789
## - m_a0 1 1.866 75.192 -30.533
## - m_sweep2 1 1.923 75.249 -30.439
## - m_whorliness 1 2.282 75.608 -29.855
## - m_waist 1 3.945 77.271 -27.178
## - hw.vfrac 1 14.089 87.415 -12.006
## - SWV 1 117.154 190.480 83.796
##
## Step: AIC=-33.57
## E.avg.dyn ~ m_volume + SWV + m_led + m_sed + m_a0 + m_a1 + m_taper +
## m_waist + m_ovality + m_whorliness + m_sweep1 + m_sweep2 +
## weight + hw.vfrac
##
## Df Sum of Sq RSS AIC
## - m_ovality 1 0.126 73.482 -35.363
## - m_sed 1 0.365 73.721 -34.964
## - m_volume 1 1.030 74.385 -33.860
## - m_sweep1 1 1.116 74.472 -33.717
## <none> 73.355 -33.575
## - m_led 1 1.413 74.768 -33.228
## - m_a0 1 1.855 75.211 -32.503
## - m_sweep2 1 1.902 75.257 -32.427
## - m_whorliness 1 2.300 75.655 -31.778
## - weight 1 2.835 76.191 -30.910
## - m_a1 1 3.768 77.124 -29.413
## - m_waist 1 4.457 77.812 -28.320
## - m_taper 1 5.693 79.048 -26.382
## - hw.vfrac 1 15.493 88.849 -12.006
## - SWV 1 117.580 190.936 82.089
##
## Step: AIC=-35.36
## E.avg.dyn ~ m_volume + SWV + m_led + m_sed + m_a0 + m_a1 + m_taper +
## m_waist + m_whorliness + m_sweep1 + m_sweep2 + weight + hw.vfrac
##
## Df Sum of Sq RSS AIC
## - m_sed 1 0.398 73.879 -36.699
## - m_volume 1 1.007 74.489 -35.689
## - m_sweep1 1 1.204 74.685 -35.365
## <none> 73.482 -35.363
## - m_led 1 1.395 74.877 -35.050
## - m_a0 1 1.834 75.315 -34.331
## - m_sweep2 1 2.029 75.511 -34.013
## - m_whorliness 1 2.421 75.903 -33.375
## - weight 1 2.728 76.209 -32.880
## - m_a1 1 3.926 77.408 -30.961
## - m_waist 1 4.618 78.100 -29.866
## - m_taper 1 5.818 79.300 -27.990
## - hw.vfrac 1 15.604 89.086 -13.677
## - SWV 1 117.475 190.957 80.103
##
## Step: AIC=-36.7
## E.avg.dyn ~ m_volume + SWV + m_led + m_a0 + m_a1 + m_taper +
## m_waist + m_whorliness + m_sweep1 + m_sweep2 + weight + hw.vfrac
##
## Df Sum of Sq RSS AIC
## - m_volume 1 1.139 75.018 -36.818
## <none> 73.879 -36.699
## - m_sweep1 1 1.238 75.118 -36.655
## - m_led 1 1.265 75.145 -36.610
## - m_a0 1 1.438 75.318 -36.328
## - m_sweep2 1 1.851 75.730 -35.656
## - weight 1 3.080 76.959 -33.676
## - m_whorliness 1 3.336 77.215 -33.267
## - m_a1 1 4.134 78.013 -32.002
## - m_waist 1 4.782 78.661 -30.986
## - m_taper 1 5.829 79.709 -29.358
## - hw.vfrac 1 15.211 89.090 -15.672
## - SWV 1 120.037 193.917 79.995
##
## Step: AIC=-36.82
## E.avg.dyn ~ SWV + m_led + m_a0 + m_a1 + m_taper + m_waist + m_whorliness +
## m_sweep1 + m_sweep2 + weight + hw.vfrac
##
## Df Sum of Sq RSS AIC
## <none> 75.018 -36.818
## - m_sweep1 1 1.238 76.257 -36.804
## - m_led 1 1.293 76.311 -36.716
## - m_sweep2 1 1.794 76.812 -35.911
## - m_a0 1 1.823 76.842 -35.864
## - weight 1 1.946 76.964 -35.668
## - m_whorliness 1 2.944 77.962 -34.084
## - m_a1 1 3.535 78.553 -33.154
## - m_waist 1 4.188 79.206 -32.136
## - m_taper 1 5.270 80.288 -30.467
## - hw.vfrac 1 23.134 98.152 -5.756
## - SWV 1 121.581 196.599 79.685
summary(m.best <- step(lm(E.avg.dyn ~ SWV, L, subset=!is.na(L$m_sed)), direction="forward", scope=E.avg.dyn ~ (SWV+m_volume+m_led+m_sed+m_a0+m_a1+m_a2+m_taper+m_waist+m_ovality+m_whorliness+m_sweep1+m_sweep2+volume+weight+density+hw.vfrac)))
## Start: AIC=46.09
## E.avg.dyn ~ SWV
##
## Df Sum of Sq RSS AIC
## + density 1 74.451 98.731 -21.033
## + hw.vfrac 1 69.439 103.743 -14.942
## + weight 1 22.385 150.797 31.061
## + m_whorliness 1 14.345 158.837 37.450
## + m_volume 1 13.835 159.347 37.845
## + volume 1 13.670 159.512 37.972
## + m_led 1 13.307 159.875 38.251
## + m_sed 1 13.042 160.140 38.455
## + m_a0 1 12.491 160.691 38.878
## + m_sweep2 1 11.279 161.903 39.802
## + m_waist 1 8.033 165.149 42.244
## + m_a2 1 7.538 165.644 42.611
## + m_a1 1 4.715 168.467 44.690
## <none> 173.182 46.085
## + m_taper 1 2.250 170.932 46.477
## + m_sweep1 1 0.733 172.449 47.564
## + m_ovality 1 0.340 172.842 47.844
##
## Step: AIC=-21.03
## E.avg.dyn ~ SWV + density
##
## Df Sum of Sq RSS AIC
## + m_volume 1 7.1502 91.581 -28.280
## + weight 1 6.9274 91.804 -27.981
## + volume 1 6.8520 91.879 -27.880
## + m_led 1 6.6487 92.083 -27.608
## + m_sed 1 6.5294 92.202 -27.449
## + m_whorliness 1 6.4331 92.298 -27.320
## + m_a0 1 6.2452 92.486 -27.070
## + m_waist 1 5.7850 92.946 -26.460
## + hw.vfrac 1 5.7087 93.023 -26.359
## + m_a2 1 5.5557 93.176 -26.157
## + m_a1 1 3.8253 94.906 -23.894
## + m_sweep2 1 2.4860 96.245 -22.170
## <none> 98.731 -21.033
## + m_taper 1 1.0487 97.683 -20.347
## + m_ovality 1 0.7039 98.027 -19.913
## + m_sweep1 1 0.0434 98.688 -19.087
##
## Step: AIC=-28.28
## E.avg.dyn ~ SWV + density + m_volume
##
## Df Sum of Sq RSS AIC
## + m_whorliness 1 8.5640 83.017 -38.356
## + hw.vfrac 1 4.9470 86.634 -33.110
## + m_waist 1 2.6065 88.975 -29.831
## + m_a2 1 2.3921 89.189 -29.535
## + m_sweep2 1 2.2594 89.322 -29.352
## + m_a1 1 1.8069 89.774 -28.731
## <none> 91.581 -28.280
## + m_a0 1 0.5657 91.015 -27.042
## + m_ovality 1 0.3021 91.279 -26.686
## + volume 1 0.2982 91.283 -26.681
## + m_taper 1 0.1968 91.384 -26.545
## + m_sed 1 0.1609 91.420 -26.496
## + weight 1 0.0699 91.511 -26.374
## + m_sweep1 1 0.0434 91.538 -26.338
## + m_led 1 0.0341 91.547 -26.326
##
## Step: AIC=-38.36
## E.avg.dyn ~ SWV + density + m_volume + m_whorliness
##
## Df Sum of Sq RSS AIC
## + hw.vfrac 1 2.69595 80.321 -40.416
## + m_waist 1 2.52990 80.487 -40.162
## + m_a2 1 2.24176 80.775 -39.723
## <none> 83.017 -38.356
## + m_a1 1 1.25284 81.764 -38.226
## + m_taper 1 0.77544 82.242 -37.510
## + m_led 1 0.49771 82.519 -37.095
## + m_sweep2 1 0.19103 82.826 -36.639
## + weight 1 0.13808 82.879 -36.561
## + m_sweep1 1 0.09530 82.922 -36.497
## + m_ovality 1 0.08065 82.937 -36.475
## + volume 1 0.06109 82.956 -36.446
## + m_sed 1 0.05569 82.962 -36.438
## + m_a0 1 0.05225 82.965 -36.433
##
## Step: AIC=-40.42
## E.avg.dyn ~ SWV + density + m_volume + m_whorliness + hw.vfrac
##
## Df Sum of Sq RSS AIC
## + m_waist 1 3.8092 76.512 -44.393
## + m_a2 1 3.4295 76.892 -43.784
## + m_a1 1 1.9948 78.326 -41.510
## <none> 80.321 -40.416
## + m_led 1 1.1312 79.190 -40.161
## + m_taper 1 0.9708 79.350 -39.912
## + m_sweep2 1 0.4281 79.893 -39.074
## + m_sweep1 1 0.2916 80.030 -38.864
## + weight 1 0.2558 80.065 -38.809
## + m_ovality 1 0.1628 80.158 -38.666
## + volume 1 0.1121 80.209 -38.588
## + m_sed 1 0.0034 80.318 -38.422
## + m_a0 1 0.0027 80.319 -38.421
##
## Step: AIC=-44.39
## E.avg.dyn ~ SWV + density + m_volume + m_whorliness + hw.vfrac +
## m_waist
##
## Df Sum of Sq RSS AIC
## + m_a2 1 2.94365 73.568 -47.218
## <none> 76.512 -44.393
## + m_sweep2 1 0.91659 75.595 -43.875
## + m_a1 1 0.63481 75.877 -43.417
## + weight 1 0.39181 76.120 -43.024
## + m_taper 1 0.33483 76.177 -42.932
## + m_a0 1 0.31077 76.201 -42.893
## + m_ovality 1 0.29777 76.214 -42.872
## + volume 1 0.28011 76.232 -42.844
## + m_sweep1 1 0.18036 76.332 -42.683
## + m_led 1 0.12038 76.392 -42.586
## + m_sed 1 0.06766 76.444 -42.501
##
## Step: AIC=-47.22
## E.avg.dyn ~ SWV + density + m_volume + m_whorliness + hw.vfrac +
## m_waist + m_a2
##
## Df Sum of Sq RSS AIC
## + weight 1 1.74944 71.819 -48.178
## + volume 1 1.63239 71.936 -47.978
## <none> 73.568 -47.218
## + m_sweep2 1 1.08297 72.485 -47.042
## + m_a0 1 0.88901 72.679 -46.714
## + m_sed 1 0.57712 72.991 -46.187
## + m_sweep1 1 0.50842 73.060 -46.071
## + m_ovality 1 0.21223 73.356 -45.574
## + m_a1 1 0.16422 73.404 -45.493
## + m_taper 1 0.10425 73.464 -45.393
## + m_led 1 0.07246 73.496 -45.339
##
## Step: AIC=-48.18
## E.avg.dyn ~ SWV + density + m_volume + m_whorliness + hw.vfrac +
## m_waist + m_a2 + weight
##
## Df Sum of Sq RSS AIC
## <none> 71.819 -48.178
## + m_sweep2 1 0.73721 71.082 -47.448
## + m_sweep1 1 0.47349 71.345 -46.992
## + m_a0 1 0.28728 71.532 -46.671
## + m_sed 1 0.11080 71.708 -46.368
## + m_taper 1 0.07267 71.746 -46.303
## + m_a1 1 0.06520 71.754 -46.290
## + m_ovality 1 0.06427 71.755 -46.289
## + volume 1 0.05954 71.759 -46.280
## + m_led 1 0.00016 71.819 -46.179
##
## Call:
## lm(formula = E.avg.dyn ~ SWV + density + m_volume + m_whorliness +
## hw.vfrac + m_waist + m_a2 + weight, data = L, subset = !is.na(L$m_sed))
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.7188 -0.3894 -0.0142 0.4668 1.6611
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.481e+01 2.507e+00 -5.909 3.64e-08 ***
## SWV 5.044e-03 3.339e-04 15.108 < 2e-16 ***
## density 8.795e-03 2.283e-03 3.853 0.000194 ***
## m_volume 8.452e+00 4.310e+00 1.961 0.052331 .
## m_whorliness -9.294e-01 2.709e-01 -3.430 0.000840 ***
## hw.vfrac -3.476e+00 1.260e+00 -2.758 0.006782 **
## m_waist 1.269e+01 4.630e+00 2.741 0.007107 **
## m_a2 -1.329e-01 5.087e-02 -2.613 0.010186 *
## weight -6.934e-03 4.161e-03 -1.666 0.098377 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7937 on 114 degrees of freedom
## Multiple R-squared: 0.7588, Adjusted R-squared: 0.7419
## F-statistic: 44.84 on 8 and 114 DF, p-value: < 2.2e-16
summary(m.best.interactions <- step(lm(E.avg.dyn ~ SWV, L, subset=!is.na(L$m_sed)), direction="forward", scope=E.avg.dyn ~ (SWV+m_volume+m_led+m_sed+m_a0+m_a1+m_a2+m_taper+m_waist+m_ovality+m_whorliness+m_sweep1+m_sweep2+weight+density+hw.vfrac)^2))
## Start: AIC=46.09
## E.avg.dyn ~ SWV
##
## Df Sum of Sq RSS AIC
## + density 1 74.451 98.731 -21.033
## + hw.vfrac 1 69.439 103.743 -14.942
## + weight 1 22.385 150.797 31.061
## + m_whorliness 1 14.345 158.837 37.450
## + m_volume 1 13.835 159.347 37.845
## + m_led 1 13.307 159.875 38.251
## + m_sed 1 13.042 160.140 38.455
## + m_a0 1 12.491 160.691 38.878
## + m_sweep2 1 11.279 161.903 39.802
## + m_waist 1 8.033 165.149 42.244
## + m_a2 1 7.538 165.644 42.611
## + m_a1 1 4.715 168.467 44.690
## <none> 173.182 46.085
## + m_taper 1 2.250 170.932 46.477
## + m_sweep1 1 0.733 172.449 47.564
## + m_ovality 1 0.340 172.842 47.844
##
## Step: AIC=-21.03
## E.avg.dyn ~ SWV + density
##
## Df Sum of Sq RSS AIC
## + m_volume 1 7.1502 91.581 -28.280
## + weight 1 6.9274 91.804 -27.981
## + m_led 1 6.6487 92.083 -27.608
## + m_sed 1 6.5294 92.202 -27.449
## + m_whorliness 1 6.4331 92.298 -27.320
## + m_a0 1 6.2452 92.486 -27.070
## + m_waist 1 5.7850 92.946 -26.460
## + hw.vfrac 1 5.7087 93.023 -26.359
## + m_a2 1 5.5557 93.176 -26.157
## + m_a1 1 3.8253 94.906 -23.894
## + m_sweep2 1 2.4860 96.245 -22.170
## <none> 98.731 -21.033
## + m_taper 1 1.0487 97.683 -20.347
## + m_ovality 1 0.7039 98.027 -19.913
## + SWV:density 1 0.2022 98.529 -19.285
## + m_sweep1 1 0.0434 98.688 -19.087
##
## Step: AIC=-28.28
## E.avg.dyn ~ SWV + density + m_volume
##
## Df Sum of Sq RSS AIC
## + m_whorliness 1 8.5640 83.017 -38.356
## + hw.vfrac 1 4.9470 86.634 -33.110
## + m_waist 1 2.6065 88.975 -29.831
## + m_a2 1 2.3921 89.189 -29.535
## + m_sweep2 1 2.2594 89.322 -29.352
## + m_a1 1 1.8069 89.774 -28.731
## <none> 91.581 -28.280
## + m_a0 1 0.5657 91.015 -27.042
## + m_ovality 1 0.3021 91.279 -26.686
## + m_taper 1 0.1968 91.384 -26.545
## + m_sed 1 0.1609 91.420 -26.496
## + SWV:density 1 0.1336 91.448 -26.459
## + weight 1 0.0699 91.511 -26.374
## + m_volume:density 1 0.0640 91.517 -26.366
## + m_sweep1 1 0.0434 91.538 -26.338
## + SWV:m_volume 1 0.0407 91.540 -26.335
## + m_led 1 0.0341 91.547 -26.326
##
## Step: AIC=-38.36
## E.avg.dyn ~ SWV + density + m_volume + m_whorliness
##
## Df Sum of Sq RSS AIC
## + hw.vfrac 1 2.69595 80.321 -40.416
## + m_waist 1 2.52990 80.487 -40.162
## + m_a2 1 2.24176 80.775 -39.723
## <none> 83.017 -38.356
## + m_a1 1 1.25284 81.764 -38.226
## + m_taper 1 0.77544 82.242 -37.510
## + SWV:m_whorliness 1 0.58717 82.430 -37.229
## + m_led 1 0.49771 82.519 -37.095
## + m_volume:m_whorliness 1 0.36156 82.656 -36.893
## + SWV:density 1 0.27611 82.741 -36.766
## + m_volume:density 1 0.24858 82.769 -36.725
## + m_sweep2 1 0.19103 82.826 -36.639
## + SWV:m_volume 1 0.18907 82.828 -36.636
## + weight 1 0.13808 82.879 -36.561
## + m_sweep1 1 0.09530 82.922 -36.497
## + m_ovality 1 0.08065 82.937 -36.475
## + m_sed 1 0.05569 82.962 -36.438
## + m_a0 1 0.05225 82.965 -36.433
## + m_whorliness:density 1 0.04145 82.976 -36.417
##
## Step: AIC=-40.42
## E.avg.dyn ~ SWV + density + m_volume + m_whorliness + hw.vfrac
##
## Df Sum of Sq RSS AIC
## + m_waist 1 3.8092 76.512 -44.393
## + m_a2 1 3.4295 76.892 -43.784
## + m_a1 1 1.9948 78.326 -41.510
## <none> 80.321 -40.416
## + m_led 1 1.1312 79.190 -40.161
## + m_taper 1 0.9708 79.350 -39.912
## + m_volume:m_whorliness 1 0.6746 79.647 -39.454
## + m_volume:hw.vfrac 1 0.6349 79.686 -39.393
## + density:hw.vfrac 1 0.5142 79.807 -39.206
## + SWV:hw.vfrac 1 0.4848 79.836 -39.161
## + m_volume:density 1 0.4396 79.882 -39.091
## + m_sweep2 1 0.4281 79.893 -39.074
## + SWV:density 1 0.4109 79.910 -39.047
## + m_whorliness:density 1 0.3276 79.994 -38.919
## + m_whorliness:hw.vfrac 1 0.2997 80.022 -38.876
## + m_sweep1 1 0.2916 80.030 -38.864
## + SWV:m_volume 1 0.2875 80.034 -38.857
## + weight 1 0.2558 80.065 -38.809
## + SWV:m_whorliness 1 0.2205 80.101 -38.755
## + m_ovality 1 0.1628 80.158 -38.666
## + m_sed 1 0.0034 80.318 -38.422
## + m_a0 1 0.0027 80.319 -38.421
##
## Step: AIC=-44.39
## E.avg.dyn ~ SWV + density + m_volume + m_whorliness + hw.vfrac +
## m_waist
##
## Df Sum of Sq RSS AIC
## + m_a2 1 2.94365 73.568 -47.218
## <none> 76.512 -44.393
## + m_volume:m_waist 1 1.18025 75.332 -44.305
## + m_waist:density 1 1.09579 75.416 -44.167
## + m_sweep2 1 0.91659 75.595 -43.875
## + density:hw.vfrac 1 0.87262 75.639 -43.803
## + m_a1 1 0.63481 75.877 -43.417
## + m_waist:hw.vfrac 1 0.46971 76.042 -43.150
## + SWV:m_whorliness 1 0.45054 76.061 -43.119
## + m_volume:hw.vfrac 1 0.42593 76.086 -43.079
## + SWV:hw.vfrac 1 0.39679 76.115 -43.032
## + weight 1 0.39181 76.120 -43.024
## + m_taper 1 0.33483 76.177 -42.932
## + m_volume:density 1 0.33466 76.177 -42.932
## + SWV:m_waist 1 0.31625 76.196 -42.902
## + SWV:density 1 0.31285 76.199 -42.897
## + m_a0 1 0.31077 76.201 -42.893
## + m_ovality 1 0.29777 76.214 -42.872
## + m_waist:m_whorliness 1 0.25295 76.259 -42.800
## + m_volume:m_whorliness 1 0.22210 76.290 -42.750
## + m_sweep1 1 0.18036 76.332 -42.683
## + m_led 1 0.12038 76.392 -42.586
## + m_sed 1 0.06766 76.444 -42.501
## + SWV:m_volume 1 0.04851 76.463 -42.471
## + m_whorliness:density 1 0.03656 76.475 -42.451
## + m_whorliness:hw.vfrac 1 0.02627 76.486 -42.435
##
## Step: AIC=-47.22
## E.avg.dyn ~ SWV + density + m_volume + m_whorliness + hw.vfrac +
## m_waist + m_a2
##
## Df Sum of Sq RSS AIC
## + m_volume:m_a2 1 2.53527 71.033 -49.532
## + m_volume:m_waist 1 2.35515 71.213 -49.220
## + weight 1 1.74944 71.819 -48.178
## <none> 73.568 -47.218
## + m_sweep2 1 1.08297 72.485 -47.042
## + density:hw.vfrac 1 0.90738 72.661 -46.745
## + m_a0 1 0.88901 72.679 -46.714
## + SWV:m_whorliness 1 0.66449 72.904 -46.334
## + m_volume:hw.vfrac 1 0.58434 72.984 -46.199
## + m_sed 1 0.57712 72.991 -46.187
## + m_volume:density 1 0.54651 73.022 -46.135
## + m_sweep1 1 0.50842 73.060 -46.071
## + m_waist:density 1 0.39487 73.173 -45.880
## + m_a2:density 1 0.34476 73.224 -45.796
## + SWV:density 1 0.33746 73.231 -45.784
## + m_waist:m_whorliness 1 0.33083 73.238 -45.773
## + m_a2:m_whorliness 1 0.30408 73.264 -45.728
## + SWV:hw.vfrac 1 0.26930 73.299 -45.669
## + SWV:m_waist 1 0.26921 73.299 -45.669
## + m_volume:m_whorliness 1 0.26853 73.300 -45.668
## + SWV:m_a2 1 0.26228 73.306 -45.658
## + m_a2:m_waist 1 0.21821 73.350 -45.584
## + m_whorliness:hw.vfrac 1 0.21564 73.353 -45.579
## + m_ovality 1 0.21223 73.356 -45.574
## + m_a1 1 0.16422 73.404 -45.493
## + m_taper 1 0.10425 73.464 -45.393
## + m_waist:hw.vfrac 1 0.10345 73.465 -45.391
## + m_whorliness:density 1 0.08845 73.480 -45.366
## + m_a2:hw.vfrac 1 0.08439 73.484 -45.359
## + m_led 1 0.07246 73.496 -45.339
## + SWV:m_volume 1 0.01549 73.553 -45.244
##
## Step: AIC=-49.53
## E.avg.dyn ~ SWV + density + m_volume + m_whorliness + hw.vfrac +
## m_waist + m_a2 + m_volume:m_a2
##
## Df Sum of Sq RSS AIC
## + m_volume:m_waist 1 1.57018 69.463 -50.281
## + m_sweep2 1 1.31934 69.714 -49.838
## + weight 1 1.26043 69.773 -49.734
## <none> 71.033 -49.532
## + SWV:m_whorliness 1 1.00502 70.028 -49.284
## + density:hw.vfrac 1 0.57981 70.453 -48.540
## + m_a2:m_waist 1 0.57825 70.455 -48.537
## + m_volume:hw.vfrac 1 0.55155 70.482 -48.491
## + m_waist:m_whorliness 1 0.51048 70.523 -48.419
## + m_volume:density 1 0.47518 70.558 -48.357
## + m_a2:m_whorliness 1 0.44949 70.584 -48.313
## + m_ovality 1 0.38682 70.646 -48.203
## + SWV:density 1 0.35950 70.674 -48.156
## + m_sweep1 1 0.34644 70.687 -48.133
## + SWV:hw.vfrac 1 0.25541 70.778 -47.975
## + m_whorliness:hw.vfrac 1 0.17581 70.857 -47.837
## + m_a0 1 0.14603 70.887 -47.785
## + m_waist:density 1 0.12407 70.909 -47.747
## + m_whorliness:density 1 0.10697 70.926 -47.717
## + m_a2:density 1 0.09142 70.942 -47.690
## + m_sed 1 0.08638 70.947 -47.681
## + m_a1 1 0.06261 70.970 -47.640
## + m_a2:hw.vfrac 1 0.03294 71.000 -47.589
## + m_taper 1 0.02695 71.006 -47.578
## + m_waist:hw.vfrac 1 0.02166 71.011 -47.569
## + m_volume:m_whorliness 1 0.01672 71.016 -47.561
## + m_led 1 0.01269 71.020 -47.554
## + SWV:m_volume 1 0.00451 71.029 -47.540
## + SWV:m_waist 1 0.00196 71.031 -47.535
## + SWV:m_a2 1 0.00073 71.032 -47.533
##
## Step: AIC=-50.28
## E.avg.dyn ~ SWV + density + m_volume + m_whorliness + hw.vfrac +
## m_waist + m_a2 + m_volume:m_a2 + m_volume:m_waist
##
## Df Sum of Sq RSS AIC
## <none> 69.463 -50.281
## + weight 1 0.99580 68.467 -50.057
## + m_sweep2 1 0.97137 68.492 -50.013
## + SWV:m_whorliness 1 0.86391 68.599 -49.820
## + m_volume:hw.vfrac 1 0.84686 68.616 -49.790
## + density:hw.vfrac 1 0.68684 68.776 -49.503
## + m_volume:density 1 0.60743 68.855 -49.361
## + m_ovality 1 0.50946 68.953 -49.187
## + m_a2:m_waist 1 0.40809 69.055 -49.006
## + SWV:density 1 0.38337 69.080 -48.962
## + SWV:hw.vfrac 1 0.37915 69.084 -48.954
## + m_a1 1 0.35931 69.104 -48.919
## + m_led 1 0.35776 69.105 -48.916
## + m_sweep1 1 0.35636 69.107 -48.914
## + m_taper 1 0.28501 69.178 -48.787
## + m_whorliness:hw.vfrac 1 0.26693 69.196 -48.755
## + m_whorliness:density 1 0.11746 69.345 -48.489
## + m_waist:m_whorliness 1 0.11675 69.346 -48.488
## + m_a2:m_whorliness 1 0.10306 69.360 -48.464
## + m_a0 1 0.08448 69.378 -48.431
## + m_a2:hw.vfrac 1 0.08004 69.383 -48.423
## + m_waist:hw.vfrac 1 0.05293 69.410 -48.375
## + m_waist:density 1 0.04339 69.420 -48.358
## + SWV:m_volume 1 0.04069 69.422 -48.353
## + m_a2:density 1 0.02438 69.439 -48.324
## + m_volume:m_whorliness 1 0.02341 69.440 -48.323
## + m_sed 1 0.02139 69.442 -48.319
## + SWV:m_a2 1 0.01786 69.445 -48.313
## + SWV:m_waist 1 0.01156 69.451 -48.302
##
## Call:
## lm(formula = E.avg.dyn ~ SWV + density + m_volume + m_whorliness +
## hw.vfrac + m_waist + m_a2 + m_volume:m_a2 + m_volume:m_waist,
## data = L, subset = !is.na(L$m_sed))
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.6882 -0.3974 -0.0021 0.4774 1.8460
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.324e+01 2.208e+00 -5.998 2.46e-08 ***
## SWV 5.141e-03 3.313e-04 15.519 < 2e-16 ***
## density 6.740e-03 1.836e-03 3.671 0.00037 ***
## m_volume 7.543e-01 5.060e-01 1.491 0.13882
## m_whorliness -7.338e-01 2.764e-01 -2.655 0.00907 **
## hw.vfrac -3.198e+00 1.239e+00 -2.580 0.01117 *
## m_waist 3.138e+01 1.292e+01 2.429 0.01671 *
## m_a2 -3.483e-01 1.408e-01 -2.473 0.01488 *
## m_volume:m_a2 5.013e-01 2.971e-01 1.687 0.09428 .
## m_volume:m_waist -4.394e+01 2.749e+01 -1.598 0.11279
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.784 on 113 degrees of freedom
## Multiple R-squared: 0.7667, Adjusted R-squared: 0.7482
## F-statistic: 41.27 on 9 and 113 DF, p-value: < 2.2e-16
#
m.best.current <- step(lm(E.avg.dyn ~ SWV, L, subset=!is.na(L$m_sed)), direction="forward", scope=E.avg.dyn ~ (m_volume+volume+SWV))
## Start: AIC=46.09
## E.avg.dyn ~ SWV
##
## Df Sum of Sq RSS AIC
## + m_volume 1 13.835 159.35 37.845
## + volume 1 13.670 159.51 37.972
## <none> 173.18 46.085
##
## Step: AIC=37.84
## E.avg.dyn ~ SWV + m_volume
##
## Df Sum of Sq RSS AIC
## <none> 159.35 37.845
## + volume 1 0.0109 159.34 39.836
m.best.withWeight <- step(lm(E.avg.dyn ~ SWV, L, subset=!is.na(L$m_sed)), direction="forward", scope=E.avg.dyn ~ (m_volume+volume+SWV+weight+density+hw.vfrac))
## Start: AIC=46.09
## E.avg.dyn ~ SWV
##
## Df Sum of Sq RSS AIC
## + density 1 74.451 98.731 -21.033
## + hw.vfrac 1 69.439 103.743 -14.942
## + weight 1 22.385 150.797 31.061
## + m_volume 1 13.835 159.347 37.845
## + volume 1 13.670 159.512 37.972
## <none> 173.182 46.085
##
## Step: AIC=-21.03
## E.avg.dyn ~ SWV + density
##
## Df Sum of Sq RSS AIC
## + m_volume 1 7.1502 91.581 -28.280
## + weight 1 6.9274 91.804 -27.981
## + volume 1 6.8520 91.879 -27.880
## + hw.vfrac 1 5.7087 93.023 -26.359
## <none> 98.731 -21.033
##
## Step: AIC=-28.28
## E.avg.dyn ~ SWV + density + m_volume
##
## Df Sum of Sq RSS AIC
## + hw.vfrac 1 4.9470 86.634 -33.110
## <none> 91.581 -28.280
## + volume 1 0.2982 91.283 -26.681
## + weight 1 0.0699 91.511 -26.374
##
## Step: AIC=-33.11
## E.avg.dyn ~ SWV + density + m_volume + hw.vfrac
##
## Df Sum of Sq RSS AIC
## <none> 86.634 -33.110
## + volume 1 0.37563 86.259 -31.645
## + weight 1 0.21029 86.424 -31.409
# currently measurable: SWV, volume/size, shape
# with weight: SWV, volume/size, shape, weight, density
m.best.withWeight <- step(lm(E.avg.dyn ~ SWV, L, subset=!is.na(L$m_sed)), direction="forward", scope=E.avg.dyn ~ (m_volume+volume+SWV+weight+density+hw.vfrac))
## Start: AIC=46.09
## E.avg.dyn ~ SWV
##
## Df Sum of Sq RSS AIC
## + density 1 74.451 98.731 -21.033
## + hw.vfrac 1 69.439 103.743 -14.942
## + weight 1 22.385 150.797 31.061
## + m_volume 1 13.835 159.347 37.845
## + volume 1 13.670 159.512 37.972
## <none> 173.182 46.085
##
## Step: AIC=-21.03
## E.avg.dyn ~ SWV + density
##
## Df Sum of Sq RSS AIC
## + m_volume 1 7.1502 91.581 -28.280
## + weight 1 6.9274 91.804 -27.981
## + volume 1 6.8520 91.879 -27.880
## + hw.vfrac 1 5.7087 93.023 -26.359
## <none> 98.731 -21.033
##
## Step: AIC=-28.28
## E.avg.dyn ~ SWV + density + m_volume
##
## Df Sum of Sq RSS AIC
## + hw.vfrac 1 4.9470 86.634 -33.110
## <none> 91.581 -28.280
## + volume 1 0.2982 91.283 -26.681
## + weight 1 0.0699 91.511 -26.374
##
## Step: AIC=-33.11
## E.avg.dyn ~ SWV + density + m_volume + hw.vfrac
##
## Df Sum of Sq RSS AIC
## <none> 86.634 -33.110
## + volume 1 0.37563 86.259 -31.645
## + weight 1 0.21029 86.424 -31.409
m.best.withHW <- step(lm(E.avg.dyn ~ SWV, L, subset=!is.na(L$m_sed)), direction="forward", scope=E.avg.dyn ~ (m_volume+volume+SWV+hw.vfrac))
## Start: AIC=46.09
## E.avg.dyn ~ SWV
##
## Df Sum of Sq RSS AIC
## + hw.vfrac 1 69.439 103.74 -14.942
## + m_volume 1 13.835 159.35 37.845
## + volume 1 13.670 159.51 37.972
## <none> 173.18 46.085
##
## Step: AIC=-14.94
## E.avg.dyn ~ SWV + hw.vfrac
##
## Df Sum of Sq RSS AIC
## + m_volume 1 6.7906 96.953 -21.269
## + volume 1 6.4838 97.260 -20.881
## <none> 103.743 -14.943
##
## Step: AIC=-21.27
## E.avg.dyn ~ SWV + hw.vfrac + m_volume
##
## Df Sum of Sq RSS AIC
## <none> 96.953 -21.269
## + volume 1 0.34228 96.611 -19.704
# with heartwood: SWV, volume/size, shape, weight, density, hw.vfrac
m.best.withWeightHW <- step(lm(E.avg.dyn ~ (SWV + density + weight + hw.vfrac), L))
## Start: AIC=-32.68
## E.avg.dyn ~ (SWV + density + weight + hw.vfrac)
##
## Df Sum of Sq RSS AIC
## <none> 86.940 -32.676
## - hw.vfrac 1 4.864 91.804 -27.981
## - weight 1 6.082 93.023 -26.359
## - density 1 9.077 96.017 -22.462
## - SWV 1 177.134 264.075 101.978
Plot best models for Marco:
myplot=function (m, lbl) {
print(s<-summary(m))
xyplot(m$model$E.avg.dyn ~ predict(m),
panel=function(x,y,...) {
panel.abline(c(0,1), col='grey70', lty=2)
panel.xyplot(x,y,...)},
aspect='iso',
xlab='Predicted', ylab='Actual',
main=sprintf('%s\nr^2=%0.2f',lbl,s$r.squared))
#main=lbl, sub=expression(r^2==s$r.squared))
}
grid.arrange(myplot(m.best.current, lbl="Current (SWV + volume)"),
myplot(m.best.withWeight, lbl="With Log Weight"),
myplot(m.best.withHW, lbl="With Log end HW"),
myplot(m.best, lbl="Everything"),
nrow=1,
as.table=TRUE)
##
## Call:
## lm(formula = E.avg.dyn ~ SWV + m_volume, data = L, subset = !is.na(L$m_sed))
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2835 -0.6269 0.0058 0.7533 2.6169
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -6.7180744 1.5591870 -4.309 3.38e-05 ***
## SWV 0.0045552 0.0004462 10.209 < 2e-16 ***
## m_volume 1.9280541 0.5973221 3.228 0.00161 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.152 on 120 degrees of freedom
## Multiple R-squared: 0.4649, Adjusted R-squared: 0.456
## F-statistic: 52.13 on 2 and 120 DF, p-value: < 2.2e-16
##
##
## Call:
## lm(formula = E.avg.dyn ~ SWV + density + m_volume + hw.vfrac,
## data = L, subset = !is.na(L$m_sed))
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.9763 -0.4081 0.0458 0.4933 1.7542
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.527e+01 2.327e+00 -6.564 1.47e-09 ***
## SWV 5.385e-03 3.462e-04 15.554 < 2e-16 ***
## density 7.351e-03 1.961e-03 3.749 0.000277 ***
## m_volume 1.323e+00 4.485e-01 2.950 0.003835 **
## hw.vfrac -3.361e+00 1.295e+00 -2.596 0.010636 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8568 on 118 degrees of freedom
## Multiple R-squared: 0.7091, Adjusted R-squared: 0.6992
## F-statistic: 71.9 on 4 and 118 DF, p-value: < 2.2e-16
##
##
## Call:
## lm(formula = E.avg.dyn ~ SWV + hw.vfrac + m_volume, data = L,
## subset = !is.na(L$m_sed))
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.9369 -0.4489 -0.0201 0.5021 1.9246
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -7.7219184 1.2266795 -6.295 5.33e-09 ***
## SWV 0.0054529 0.0003643 14.970 < 2e-16 ***
## hw.vfrac -7.2258935 0.8257089 -8.751 1.67e-14 ***
## m_volume 1.3635436 0.4723057 2.887 0.00462 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9026 on 119 degrees of freedom
## Multiple R-squared: 0.6744, Adjusted R-squared: 0.6662
## F-statistic: 82.17 on 3 and 119 DF, p-value: < 2.2e-16
##
##
## Call:
## lm(formula = E.avg.dyn ~ SWV + density + m_volume + m_whorliness +
## hw.vfrac + m_waist + m_a2 + weight, data = L, subset = !is.na(L$m_sed))
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.7188 -0.3894 -0.0142 0.4668 1.6611
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.481e+01 2.507e+00 -5.909 3.64e-08 ***
## SWV 5.044e-03 3.339e-04 15.108 < 2e-16 ***
## density 8.795e-03 2.283e-03 3.853 0.000194 ***
## m_volume 8.452e+00 4.310e+00 1.961 0.052331 .
## m_whorliness -9.294e-01 2.709e-01 -3.430 0.000840 ***
## hw.vfrac -3.476e+00 1.260e+00 -2.758 0.006782 **
## m_waist 1.269e+01 4.630e+00 2.741 0.007107 **
## m_a2 -1.329e-01 5.087e-02 -2.613 0.010186 *
## weight -6.934e-03 4.161e-03 -1.666 0.098377 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7937 on 114 degrees of freedom
## Multiple R-squared: 0.7588, Adjusted R-squared: 0.7419
## F-statistic: 44.84 on 8 and 114 DF, p-value: < 2.2e-16
Does eliminating logs with significant compression wood visible on ends lead to better models?
what % of lumber that is not from the cant has stiffness below 6GPa?
Use stepwise regression to select ‘best’ (in terms of AIC) linear model.
best.linear.model = function (y,LL=NULL,plot=TRUE,...) {
if (is.null(LL)) {
LL=L[,predictors]
}
LL$y = y
LL = na.omit(LL)#[complete.cases(LL),]
scope = formula(paste("y~",paste(predictors,collapse='+')))
#print(scope)
m.init <- lm(y ~ SWV, LL, ...)
#browser()
m <- step(m.init, direction="both", scope=scope, trace=0)
if (plot) {
print(xyplot(LL$y ~ predict(m),aspect='iso',
panel=function(...){
panel.abline(c(0,1),col='grey70')
panel.xyplot(...)},
main=deparse(substitute(y)),
xlab='predicted', ylab='observed'))
}
return(m)
}
summary(m.best.bow_avg <- best.linear.model(L$bow_avg))
##
## Call:
## lm(formula = y ~ SWV + density + m_taper, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -8.0477 -2.3025 -0.5719 1.8777 16.4729
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 50.130387 7.768906 6.453 2.48e-09 ***
## SWV -0.006338 0.001486 -4.265 4.04e-05 ***
## density -0.016751 0.005007 -3.345 0.00110 **
## m_taper -0.344437 0.128428 -2.682 0.00836 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.637 on 119 degrees of freedom
## Multiple R-squared: 0.1857, Adjusted R-squared: 0.1651
## F-statistic: 9.044 on 3 and 119 DF, p-value: 1.925e-05
summary(m.best.bow_p50 <- best.linear.model(L$bow_p50))
##
## Call:
## lm(formula = y ~ SWV + density + m_led + m_a0 + m_whorliness +
## weight, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.7477 -2.4296 -0.4523 2.1092 11.6209
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 48.036399 11.206653 4.286 3.77e-05 ***
## SWV -0.007397 0.001610 -4.594 1.11e-05 ***
## density -0.014851 0.006826 -2.176 0.0316 *
## m_led -0.054103 0.029463 -1.836 0.0689 .
## m_a0 0.089035 0.035585 2.502 0.0137 *
## m_whorliness -2.859383 1.304531 -2.192 0.0304 *
## weight -0.017303 0.012097 -1.430 0.1553
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.762 on 116 degrees of freedom
## Multiple R-squared: 0.2656, Adjusted R-squared: 0.2276
## F-statistic: 6.991 on 6 and 116 DF, p-value: 2.304e-06
summary(m.best.bow_p75 <- best.linear.model(L$bow_p75))
##
## Call:
## lm(formula = y ~ SWV + m_taper + density, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -10.9639 -3.2509 -0.4905 3.2151 20.5563
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 62.605957 10.910506 5.738 7.43e-08 ***
## SWV -0.007785 0.002087 -3.730 0.000295 ***
## m_taper -0.532468 0.180362 -2.952 0.003802 **
## density -0.019486 0.007032 -2.771 0.006483 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 5.108 on 119 degrees of freedom
## Multiple R-squared: 0.1575, Adjusted R-squared: 0.1363
## F-statistic: 7.417 on 3 and 119 DF, p-value: 0.0001348
SWV, weight, density, whorliness and taper best predictors. Median bow best predicted.
summary(m.best.crook_avg <- best.linear.model(L$crook_avg))
##
## Call:
## lm(formula = y ~ density + sweep.prod + m_a2, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.4455 -1.4960 -0.3582 0.9658 10.4465
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 11.763314 2.899084 4.058 8.9e-05 ***
## density -0.007900 0.003032 -2.605 0.0104 *
## sweep.prod 1.885969 0.839433 2.247 0.0265 *
## m_a2 -0.012981 0.006966 -1.863 0.0649 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.238 on 119 degrees of freedom
## Multiple R-squared: 0.1293, Adjusted R-squared: 0.1073
## F-statistic: 5.888 on 3 and 119 DF, p-value: 0.0008794
summary(m.best.crook_p50 <- best.linear.model(L$crook_p50))
##
## Call:
## lm(formula = y ~ SWV + hw.vfrac + sweep.prod + m_taper, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.6810 -1.3799 -0.4174 0.8419 8.7215
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 9.8372683 3.2768419 3.002 0.00327 **
## SWV -0.0020108 0.0009157 -2.196 0.03005 *
## hw.vfrac 6.2981503 1.9614745 3.211 0.00171 **
## sweep.prod 1.6186090 0.8178916 1.979 0.05014 .
## m_taper -0.1322546 0.0747625 -1.769 0.07948 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.119 on 118 degrees of freedom
## Multiple R-squared: 0.1552, Adjusted R-squared: 0.1265
## F-statistic: 5.418 on 4 and 118 DF, p-value: 0.0004857
summary(m.best.crook_p75 <- best.linear.model(L$crook_p75))
##
## Call:
## lm(formula = y ~ SWV + density + sweep.prod + m_taper, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.1687 -1.9566 -0.6777 1.1977 14.4027
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 28.177452 6.780630 4.156 6.17e-05 ***
## SWV -0.002311 0.001259 -1.835 0.06901 .
## density -0.014306 0.004252 -3.365 0.00103 **
## sweep.prod 2.691696 1.167080 2.306 0.02284 *
## m_taper -0.165324 0.106147 -1.557 0.12203
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.001 on 118 degrees of freedom
## Multiple R-squared: 0.1772, Adjusted R-squared: 0.1493
## F-statistic: 6.355 on 4 and 118 DF, p-value: 0.0001149
75%ile crook best predicted. Density, sweep.prod, SWV, whorliness.
Stan combined bow and crook using WPA grade limits.
combined_warp = L$crook_avg/75 + L$bow_avg/25
summary(m.best.combined_warp <- best.linear.model(combined_warp))
##
## Call:
## lm(formula = y ~ SWV + density + m_taper, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.32265 -0.09364 -0.01027 0.06659 0.73476
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.3008456 0.3288043 6.998 1.65e-10 ***
## SWV -0.0002806 0.0000629 -4.461 1.87e-05 ***
## density -0.0008098 0.0002119 -3.822 0.000212 ***
## m_taper -0.0149063 0.0054355 -2.742 0.007042 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1539 on 119 degrees of freedom
## Multiple R-squared: 0.2091, Adjusted R-squared: 0.1892
## F-statistic: 10.49 on 3 and 119 DF, p-value: 3.575e-06
What happens if we toss a couple of outliers?
L$SWILogNumber[combined_warp>1.2] # 222
## [1] 222
L$SWILogNumber[combined_warp<0.2] # 103
## [1] 103
subset = !L$SWILogNumber%in%c(103,222)
summary(m.best.combined_warp <- best.linear.model(combined_warp[subset], LL=L[subset,predictors]))
##
## Call:
## lm(formula = y ~ SWV + density + m_taper + weight, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.25644 -0.09717 -0.01417 0.07387 0.39249
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.151e+00 2.904e-01 7.409 2.23e-11 ***
## SWV -2.719e-04 5.655e-05 -4.808 4.61e-06 ***
## density -6.330e-04 1.934e-04 -3.274 0.00140 **
## m_taper -1.561e-02 4.916e-03 -3.176 0.00191 **
## weight -9.961e-05 7.043e-05 -1.414 0.15991
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1353 on 116 degrees of freedom
## Multiple R-squared: 0.2465, Adjusted R-squared: 0.2205
## F-statistic: 9.486 on 4 and 116 DF, p-value: 1.138e-06
A little better, but nothing spectacular.
Can a random forest model do better?
LL=L[,predictors]
LL$combined_warp = combined_warp
LL = na.omit(LL)
m.rf <- randomForest(combined_warp ~ ., LL, importance=TRUE, ntree=50000)
par(mfcol=c(1,1))
varImpPlot(m.rf)
print(m.rf)
##
## Call:
## randomForest(formula = combined_warp ~ ., data = LL, importance = TRUE, ntree = 50000)
## Type of random forest: regression
## Number of trees: 50000
## No. of variables tried at each split: 5
##
## Mean of squared residuals: 0.02992237
## % Var explained: -3.22
xyplot(LL$combined_warp ~ predict(m.rf), aspect='iso')
Lousy results, but interesting that log green density turns up as the most favoured predictor, followed by SWV, taper and ovality.
What about other variable selection approaches?
LL <- L[,predictors]
for (lmeas in c('E.avg.dyn','crook_avg','crook_avg_inner','crook_avg_outer','bow_avg','twist_avg')) {
LL$y = L[,lmeas]
m.0 <- lm(y ~ ., LL)
Hmat <- lmHmat(m.0)
Eleaps <- eleaps(Hmat$mat, kmin=1, kmax=length(predictors)-1, H=Hmat$H, r=Hmat$r)
plot(Eleaps$bestvalues, type='b', main=lmeas, ylab="model goodness", xlab="number of predictors")
cat(paste("\n",lmeas,"\n"))
for (i in 1:nrow(Eleaps$bestsets)) {
cat(paste(i,': ',paste(colnames(Hmat$mat)[Eleaps$bestsets[i,1:i]],collapse=", "),"\n", sep=""))
# AIC?
}
}
##
## E.avg.dyn
## 1: SWV
## 2: SWV, density
## 3: SWV, m_volume, density
## 4: SWV, m_led, m_whorliness, density
## 5: SWV, m_led, m_whorliness, density, hw.vfrac
## 6: SWV, m_led, m_waist, m_whorliness, density, hw.vfrac
## 7: SWV, m_volume, m_a2, m_waist, m_whorliness, density, hw.vfrac
## 8: SWV, m_volume, m_a2, m_waist, m_whorliness, weight, density, hw.vfrac
## 9: SWV, m_volume, m_a2, m_waist, m_whorliness, m_sweep2, weight, density, hw.vfrac
## 10: SWV, m_volume, m_a2, m_waist, m_whorliness, m_sweep1, weight, density, hw.vfrac, sweep.prod
## 11: SWV, m_volume, m_a0, m_a2, m_waist, m_whorliness, m_sweep1, weight, density, hw.vfrac, sweep.prod
## 12: SWV, m_volume, m_led, m_a0, m_a2, m_taper, m_waist, m_whorliness, m_sweep1, density, hw.vfrac, sweep.prod
## 13: SWV, m_volume, m_led, m_a0, m_a1, m_a2, m_waist, m_whorliness, m_sweep1, weight, density, hw.vfrac, sweep.prod
## 14: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_waist, m_whorliness, m_sweep1, weight, density, hw.vfrac, sweep.prod
## 15: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_waist, m_ovality, m_whorliness, m_sweep1, weight, density, hw.vfrac, sweep.prod
## 16: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_whorliness, m_sweep1, weight, density, hw.vfrac, sweep.prod
##
## crook_avg
## 1: density
## 2: density, sweep.prod
## 3: m_a2, density, sweep.prod
## 4: SWV, m_a2, density, sweep.prod
## 5: m_a1, m_taper, m_waist, density, sweep.prod
## 6: SWV, m_a1, m_taper, m_waist, density, sweep.prod
## 7: SWV, m_a1, m_taper, m_waist, density, hw.vfrac, sweep.prod
## 8: SWV, m_a1, m_taper, m_waist, m_whorliness, density, hw.vfrac, sweep.prod
## 9: SWV, m_a1, m_a2, m_taper, m_waist, m_whorliness, density, hw.vfrac, sweep.prod
## 10: SWV, m_sed, m_a0, m_a1, m_taper, m_waist, m_whorliness, density, hw.vfrac, sweep.prod
## 11: SWV, m_volume, m_a1, m_a2, m_taper, m_waist, m_whorliness, weight, density, hw.vfrac, sweep.prod
## 12: SWV, m_volume, m_led, m_a1, m_a2, m_taper, m_waist, m_whorliness, weight, density, hw.vfrac, sweep.prod
## 13: SWV, m_volume, m_led, m_sed, m_a1, m_a2, m_taper, m_waist, m_whorliness, weight, density, hw.vfrac, sweep.prod
## 14: SWV, m_volume, m_led, m_sed, m_a1, m_a2, m_taper, m_waist, m_whorliness, m_sweep2, weight, density, hw.vfrac, sweep.prod
## 15: SWV, m_volume, m_led, m_sed, m_a1, m_a2, m_taper, m_waist, m_whorliness, m_sweep1, m_sweep2, weight, density, hw.vfrac, sweep.prod
## 16: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_whorliness, m_sweep1, m_sweep2, weight, density, hw.vfrac, sweep.prod
##
## crook_avg_inner
## 1: sweep.prod
## 2: m_volume, weight
## 3: SWV, m_volume, weight
## 4: m_volume, m_a1, weight, sweep.prod
## 5: SWV, m_volume, m_a2, weight, sweep.prod
## 6: SWV, m_volume, m_a2, m_waist, weight, sweep.prod
## 7: SWV, m_volume, m_a1, m_taper, m_waist, weight, sweep.prod
## 8: SWV, m_led, m_a0, m_a1, m_taper, m_waist, density, sweep.prod
## 9: SWV, m_led, m_a0, m_a1, m_a2, m_taper, m_waist, density, sweep.prod
## 10: SWV, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, density, sweep.prod
## 11: SWV, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_whorliness, density, sweep.prod
## 12: SWV, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_whorliness, density, sweep.prod
## 13: SWV, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_sweep1, m_sweep2, density, sweep.prod
## 14: SWV, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_whorliness, m_sweep1, m_sweep2, density, sweep.prod
## 15: SWV, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_whorliness, m_sweep1, m_sweep2, weight, density, sweep.prod
## 16: SWV, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_whorliness, m_sweep1, m_sweep2, weight, density, hw.vfrac, sweep.prod
##
## crook_avg_outer
## 1: m_waist
## 2: SWV, m_led
## 3: SWV, m_led, m_waist
## 4: SWV, m_sed, m_waist, m_whorliness
## 5: SWV, m_sed, m_a0, m_a2, m_whorliness
## 6: SWV, m_sed, m_a0, m_a2, m_whorliness, m_sweep1
## 7: SWV, m_sed, m_a0, m_a2, m_whorliness, m_sweep1, density
## 8: SWV, m_sed, m_a0, m_a1, m_taper, m_waist, m_whorliness, m_sweep1
## 9: SWV, m_volume, m_sed, m_a0, m_a2, m_whorliness, m_sweep1, weight, density
## 10: SWV, m_volume, m_sed, m_a0, m_a2, m_waist, m_whorliness, m_sweep1, weight, density
## 11: SWV, m_volume, m_led, m_sed, m_a0, m_a2, m_waist, m_whorliness, m_sweep1, weight, density
## 12: SWV, m_volume, m_led, m_sed, m_a0, m_a2, m_taper, m_waist, m_whorliness, m_sweep1, weight, density
## 13: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_whorliness, m_sweep1, weight, density
## 14: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_whorliness, m_sweep1, weight, density
## 15: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_whorliness, m_sweep1, weight, density, sweep.prod
## 16: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_whorliness, m_sweep1, m_sweep2, weight, density, sweep.prod
##
## bow_avg
## 1: SWV
## 2: SWV, density
## 3: SWV, m_taper, density
## 4: SWV, m_led, m_a0, density
## 5: SWV, m_led, m_a0, m_ovality, density
## 6: SWV, m_led, m_a0, m_ovality, weight, density
## 7: SWV, m_led, m_a0, m_ovality, m_whorliness, weight, density
## 8: SWV, m_volume, m_a0, m_a1, m_a2, m_taper, m_whorliness, density
## 9: SWV, m_volume, m_a0, m_a1, m_a2, m_taper, m_ovality, m_whorliness, density
## 10: SWV, m_volume, m_led, m_a0, m_a1, m_a2, m_taper, m_ovality, m_whorliness, density
## 11: SWV, m_volume, m_led, m_a0, m_a1, m_a2, m_taper, m_ovality, m_whorliness, m_sweep1, density
## 12: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_ovality, m_whorliness, m_sweep1, density
## 13: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_ovality, m_whorliness, m_sweep1, weight, density
## 14: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_ovality, m_whorliness, m_sweep1, weight, density, sweep.prod
## 15: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_ovality, m_whorliness, m_sweep1, weight, density, hw.vfrac, sweep.prod
## 16: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_ovality, m_whorliness, m_sweep1, m_sweep2, weight, density, hw.vfrac, sweep.prod
##
## twist_avg
## 1: SWV
## 2: SWV, m_led
## 3: SWV, m_volume, weight
## 4: SWV, m_volume, m_waist, weight
## 5: SWV, m_volume, m_waist, m_sweep1, weight
## 6: SWV, m_volume, m_a2, m_waist, m_sweep1, weight
## 7: SWV, m_volume, m_a1, m_taper, m_waist, m_sweep1, weight
## 8: SWV, m_volume, m_a1, m_taper, m_waist, m_ovality, m_sweep1, weight
## 9: SWV, m_volume, m_a1, m_a2, m_taper, m_waist, m_ovality, m_sweep1, density
## 10: SWV, m_volume, m_a1, m_a2, m_taper, m_waist, m_ovality, m_sweep1, m_sweep2, density
## 11: SWV, m_volume, m_led, m_a0, m_a1, m_taper, m_waist, m_ovality, m_sweep1, m_sweep2, density
## 12: SWV, m_led, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_sweep1, m_sweep2, density, hw.vfrac
## 13: SWV, m_volume, m_led, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_sweep1, m_sweep2, density, hw.vfrac
## 14: SWV, m_volume, m_led, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_whorliness, m_sweep1, m_sweep2, density, hw.vfrac
## 15: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_whorliness, m_sweep1, m_sweep2, density, hw.vfrac
## 16: SWV, m_volume, m_led, m_sed, m_a0, m_a1, m_a2, m_taper, m_waist, m_ovality, m_whorliness, m_sweep1, m_sweep2, density, hw.vfrac, sweep.prod
Note: other R packages include bestglm, subselect, leaps, glmulti.
LL <- L[,predictors]
LL$y = L$E.avg.dyn
m.0 <- glm(y ~ ., LL, family=gaussian(link="identity")) # equiv to a linear model
m.best <- glmulti(m.0, method="l", level=1) # level=1 forces no interactions
## Initialization...
## TASK: Exhaustive screening of candidate set, branch-and-bound algorithm.
## [ Be sure to have package leaps installed ]
## Fitting...
## Completed.
## 200 first best models identified.
# sloooooooow!
From ML, May 8:
To do: * Any further models needed for warp? Why are models significantly poorer than KPP – due to compression wood outliers being removed in the KPP analysis? * Is a stiffness segregation device required on the edger? i.e. what % of lumber that is not from the cant has stiffness below 6GPa? If this is a major lets drop it. * Do we need to say anything about the mc data (NMI and aquascan)? A comment on importance of mc in warp expression and the variability we saw would be useful. * Any further implications for JNL trial?
grid.arrange(
xyplot(E.gradient ~ E.d.hitman_avg, L),
xyplot(E.gradient ~ volume, L),
ncol=2)
Reasonable range in inner:outer stiffness. Independent of overall stiffness and size.
See models below.
summary(m <- best.linear.model(L$crook_avg))
##
## Call:
## lm(formula = y ~ density + sweep.prod + m_a2, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.4455 -1.4960 -0.3582 0.9658 10.4465
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 11.763314 2.899084 4.058 8.9e-05 ***
## density -0.007900 0.003032 -2.605 0.0104 *
## sweep.prod 1.885969 0.839433 2.247 0.0265 *
## m_a2 -0.012981 0.006966 -1.863 0.0649 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.238 on 119 degrees of freedom
## Multiple R-squared: 0.1293, Adjusted R-squared: 0.1073
## F-statistic: 5.888 on 3 and 119 DF, p-value: 0.0008794
summary(m <- best.linear.model(L$crook_avg_inner))
##
## Call:
## lm(formula = y ~ SWV + m_volume + weight, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.8585 -2.2262 -0.9317 1.9024 14.3969
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 13.692827 4.710130 2.907 0.004371 **
## SWV -0.002810 0.001344 -2.091 0.038756 *
## m_volume 40.881127 10.858042 3.765 0.000263 ***
## weight -0.036638 0.010143 -3.612 0.000450 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.388 on 116 degrees of freedom
## Multiple R-squared: 0.1348, Adjusted R-squared: 0.1124
## F-statistic: 6.026 on 3 and 116 DF, p-value: 0.0007514
summary(m <- best.linear.model(L$crook_avg_outer))
##
## Call:
## lm(formula = y ~ SWV + m_led, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -5.0260 -1.6590 -0.2693 1.2890 10.3030
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 17.896113 4.321842 4.141 7.05e-05 ***
## SWV -0.003170 0.001128 -2.809 0.00593 **
## m_led -0.008465 0.003714 -2.280 0.02467 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.638 on 104 degrees of freedom
## Multiple R-squared: 0.08801, Adjusted R-squared: 0.07047
## F-statistic: 5.018 on 2 and 104 DF, p-value: 0.008308
Best inner and outer models are both WORSE than total!
summary(m <- best.linear.model(L$bow_avg))
##
## Call:
## lm(formula = y ~ SWV + density + m_taper, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -8.0477 -2.3025 -0.5719 1.8777 16.4729
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 50.130387 7.768906 6.453 2.48e-09 ***
## SWV -0.006338 0.001486 -4.265 4.04e-05 ***
## density -0.016751 0.005007 -3.345 0.00110 **
## m_taper -0.344437 0.128428 -2.682 0.00836 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.637 on 119 degrees of freedom
## Multiple R-squared: 0.1857, Adjusted R-squared: 0.1651
## F-statistic: 9.044 on 3 and 119 DF, p-value: 1.925e-05
summary(m <- best.linear.model(L$bow_avg_inner))
##
## Call:
## lm(formula = y ~ SWV + m_ovality + density + m_taper + m_a2 +
## m_a1, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.588 -3.326 -0.567 2.560 17.202
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.375e+01 1.099e+01 4.891 3.35e-06 ***
## SWV -8.798e-03 2.102e-03 -4.186 5.65e-05 ***
## m_ovality 1.686e+03 6.535e+02 2.580 0.01116 *
## density -1.189e-02 6.972e-03 -1.706 0.09078 .
## m_taper -5.683e+00 1.801e+00 -3.155 0.00205 **
## m_a2 1.152e+00 3.796e-01 3.035 0.00299 **
## m_a1 1.124e+00 3.784e-01 2.971 0.00363 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 5.035 on 113 degrees of freedom
## Multiple R-squared: 0.2349, Adjusted R-squared: 0.1943
## F-statistic: 5.782 on 6 and 113 DF, p-value: 2.798e-05
summary(m <- best.linear.model(L$bow_avg_outer))
##
## Call:
## lm(formula = y ~ SWV + density + m_taper, data = LL)
##
## Residuals:
## Min 1Q Median 3Q Max
## -10.252 -3.351 -1.038 2.422 29.742
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 79.129663 14.626657 5.410 4.12e-07 ***
## SWV -0.010528 0.002726 -3.862 0.000197 ***
## density -0.031996 0.009811 -3.261 0.001505 **
## m_taper -0.506055 0.223307 -2.266 0.025531 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 6.205 on 103 degrees of freedom
## Multiple R-squared: 0.1841, Adjusted R-squared: 0.1603
## F-statistic: 7.746 on 3 and 103 DF, p-value: 0.0001026
Do logs with lousy inner boards also have lousy outer boards?
xyplot(crook_avg_outer ~ crook_avg_inner, L)
xyplot(bow_avg_outer ~ bow_avg_inner, L)
xyplot(twist_avg_outer ~ twist_avg_inner, L)
No. Outer and Inner pretty much uncorrelated.
If we look only at subsets of logs that are in some way ‘good’, do we get similar prediction models?
Fit models only to logs Marco identified as not appearing to contain significant CW based on log end imagery.
both.ends.severe.cw = c(189, 210, 212, 222)
both.ends.moderate.cw = c(123, 135, 144, 159, 178, 188, 190, 208)
for (lmeas in log.quality.measures) {
models <- cf.full(lmeas, idx.sub=!L$SWILogNumber%in%union(both.ends.severe.cw,both.ends.moderate.cw))
}
Call:
lm(formula = y ~ SWV + density + m_volume + m_whorliness + hw.vfrac +
m_waist + m_a2 + weight, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.7188 -0.3894 -0.0142 0.4668 1.6611
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.481e+01 2.507e+00 -5.909 3.64e-08 ***
SWV 5.044e-03 3.339e-04 15.108 < 2e-16 ***
density 8.795e-03 2.283e-03 3.853 0.000194 ***
m_volume 8.452e+00 4.310e+00 1.961 0.052331 .
m_whorliness -9.294e-01 2.709e-01 -3.430 0.000840 ***
hw.vfrac -3.476e+00 1.260e+00 -2.758 0.006782 **
m_waist 1.269e+01 4.630e+00 2.741 0.007107 **
m_a2 -1.329e-01 5.087e-02 -2.613 0.010186 *
weight -6.934e-03 4.161e-03 -1.666 0.098377 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.7937 on 114 degrees of freedom
Multiple R-squared: 0.7588, Adjusted R-squared: 0.7419
F-statistic: 44.84 on 8 and 114 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + density + m_volume + m_whorliness + m_waist +
m_a2 + hw.vfrac + m_sweep2 + m_a0, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.5739 -0.3175 0.0217 0.4540 1.5333
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.047e+01 2.447e+00 -4.278 4.29e-05 ***
SWV 4.768e-03 3.652e-04 13.057 < 2e-16 ***
density 6.581e-03 1.932e-03 3.406 0.000946 ***
m_volume 5.065e+00 2.618e+00 1.934 0.055850 .
m_whorliness -6.711e-01 3.047e-01 -2.203 0.029878 *
m_waist 1.220e+01 4.461e+00 2.736 0.007347 **
m_a2 -1.260e-01 4.891e-02 -2.576 0.011452 *
hw.vfrac -2.697e+00 1.305e+00 -2.067 0.041336 *
m_sweep2 -1.142e+00 7.638e-01 -1.495 0.138099
m_a0 -1.007e-02 6.810e-03 -1.478 0.142449
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.7889 on 101 degrees of freedom
Multiple R-squared: 0.7525, Adjusted R-squared: 0.7304
F-statistic: 34.11 on 9 and 101 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + density + m_volume + m_whorliness + hw.vfrac +
m_waist + m_a2 + weight, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.7188 -0.3894 -0.0142 0.4668 1.6611
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.481e+01 2.507e+00 -5.909 3.64e-08 ***
SWV 5.044e-03 3.339e-04 15.108 < 2e-16 ***
density 8.795e-03 2.283e-03 3.853 0.000194 ***
m_volume 8.452e+00 4.310e+00 1.961 0.052331 .
m_whorliness -9.294e-01 2.709e-01 -3.430 0.000840 ***
hw.vfrac -3.476e+00 1.260e+00 -2.758 0.006782 **
m_waist 1.269e+01 4.630e+00 2.741 0.007107 **
m_a2 -1.329e-01 5.087e-02 -2.613 0.010186 *
weight -6.934e-03 4.161e-03 -1.666 0.098377 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.7937 on 114 degrees of freedom
Multiple R-squared: 0.7588, Adjusted R-squared: 0.7419
F-statistic: 44.84 on 8 and 114 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + density + m_volume + m_whorliness + m_waist +
m_a2 + hw.vfrac + m_sweep2 + m_a0, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.5739 -0.3175 0.0217 0.4540 1.5333
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.047e+01 2.447e+00 -4.278 4.29e-05 ***
SWV 4.768e-03 3.652e-04 13.057 < 2e-16 ***
density 6.581e-03 1.932e-03 3.406 0.000946 ***
m_volume 5.065e+00 2.618e+00 1.934 0.055850 .
m_whorliness -6.711e-01 3.047e-01 -2.203 0.029878 *
m_waist 1.220e+01 4.461e+00 2.736 0.007347 **
m_a2 -1.260e-01 4.891e-02 -2.576 0.011452 *
hw.vfrac -2.697e+00 1.305e+00 -2.067 0.041336 *
m_sweep2 -1.142e+00 7.638e-01 -1.495 0.138099
m_a0 -1.007e-02 6.810e-03 -1.478 0.142449
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.7889 on 101 degrees of freedom
Multiple R-squared: 0.7525, Adjusted R-squared: 0.7304
F-statistic: 34.11 on 9 and 101 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + density + m_a0 + m_whorliness, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.1729 -0.5000 -0.1065 0.6968 3.3610
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.192e+01 2.354e+00 -5.063 1.60e-06 ***
SWV 3.599e-03 4.353e-04 8.268 2.82e-13 ***
density 1.150e-02 1.530e-03 7.513 1.41e-11 ***
m_a0 -5.816e-03 1.587e-03 -3.665 0.000377 ***
m_whorliness -1.122e+00 3.675e-01 -3.054 0.002809 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.072 on 114 degrees of freedom
Multiple R-squared: 0.5955, Adjusted R-squared: 0.5813
F-statistic: 41.96 on 4 and 114 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + density + m_a0 + m_whorliness + m_ovality,
data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.0947 -0.5504 -0.0438 0.5584 3.3936
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.086e+01 2.500e+00 -4.343 3.36e-05 ***
SWV 3.464e-03 4.597e-04 7.536 2.14e-11 ***
density 1.089e-02 1.605e-03 6.785 8.06e-10 ***
m_a0 -6.062e-03 1.679e-03 -3.610 0.000478 ***
m_whorliness -1.029e+00 3.928e-01 -2.620 0.010145 *
m_ovality -2.438e+02 1.536e+02 -1.587 0.115612
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.086 on 101 degrees of freedom
Multiple R-squared: 0.5851, Adjusted R-squared: 0.5646
F-statistic: 28.49 on 5 and 101 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + hw.vfrac + sweep.prod + m_a1 + m_ovality,
data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.4250 -0.7854 0.0482 0.7849 3.4290
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -7.766e+00 1.927e+00 -4.031 0.00011 ***
SWV 6.280e-03 5.832e-04 10.768 < 2e-16 ***
hw.vfrac -7.427e+00 1.351e+00 -5.499 3.04e-07 ***
sweep.prod -1.545e+00 5.176e-01 -2.984 0.00359 **
m_a1 -1.233e-02 4.302e-03 -2.865 0.00510 **
m_ovality 3.087e+02 1.710e+02 1.805 0.07412 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.287 on 98 degrees of freedom
Multiple R-squared: 0.6554, Adjusted R-squared: 0.6379
F-statistic: 37.28 on 5 and 98 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + density + sweep.prod + m_a1 + hw.vfrac +
m_ovality, data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.1560 -0.6863 0.0343 0.8042 2.6647
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.139e+01 4.194e+00 -2.715 0.00804 **
SWV 5.770e-03 6.256e-04 9.224 1.9e-14 ***
density 4.724e-03 3.399e-03 1.390 0.16823
sweep.prod -1.628e+00 5.467e-01 -2.978 0.00378 **
m_a1 -1.035e-02 4.434e-03 -2.335 0.02193 *
hw.vfrac -4.051e+00 2.193e+00 -1.847 0.06817 .
m_ovality 3.212e+02 1.852e+02 1.735 0.08645 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.278 on 85 degrees of freedom
Multiple R-squared: 0.6435, Adjusted R-squared: 0.6183
F-statistic: 25.57 on 6 and 85 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + m_a0 + weight + sweep.prod + m_ovality +
m_waist + m_whorliness + hw.vfrac + m_volume, data = LL)
Residuals:
Min 1Q Median 3Q Max
-0.30929 -0.07260 -0.01550 0.07418 0.46518
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.593e+00 2.730e-01 5.835 8.17e-08 ***
SWV -1.022e-04 6.432e-05 -1.589 0.11554
m_a0 -2.873e-03 1.498e-03 -1.918 0.05826 .
weight 1.824e-03 6.152e-04 2.965 0.00386 **
sweep.prod 1.494e-01 5.605e-02 2.666 0.00909 **
m_ovality -4.085e+01 1.764e+01 -2.315 0.02283 *
m_waist -9.980e-02 4.626e-02 -2.157 0.03363 *
m_whorliness -1.013e-01 5.049e-02 -2.006 0.04784 *
hw.vfrac 4.014e-01 1.986e-01 2.022 0.04615 *
m_volume -9.624e-01 6.685e-01 -1.440 0.15342
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.1306 on 91 degrees of freedom
Multiple R-squared: 0.3267, Adjusted R-squared: 0.2601
F-statistic: 4.906 on 9 and 91 DF, p-value: 2.309e-05
|
Call:
lm(formula = y ~ SWV + m_a0 + m_ovality + m_a1 + sweep.prod +
m_whorliness, data = LL)
Residuals:
Min 1Q Median 3Q Max
-0.26629 -0.09705 -0.01340 0.08638 0.40959
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.255e+00 2.648e-01 4.740 8.87e-06 ***
SWV -9.189e-05 6.678e-05 -1.376 0.17260
m_a0 -5.244e-04 2.441e-04 -2.148 0.03463 *
m_ovality -5.495e+01 2.016e+01 -2.726 0.00785 **
m_a1 1.245e-03 5.240e-04 2.375 0.01988 *
sweep.prod 1.389e-01 6.114e-02 2.271 0.02575 *
m_whorliness -9.449e-02 5.480e-02 -1.724 0.08842 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.1379 on 82 degrees of freedom
Multiple R-squared: 0.2763, Adjusted R-squared: 0.2233
F-statistic: 5.217 on 6 and 82 DF, p-value: 0.0001364
|
Call:
lm(formula = y ~ density + sweep.prod + m_a2, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.4455 -1.4960 -0.3582 0.9658 10.4465
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 11.763314 2.899084 4.058 8.9e-05 ***
density -0.007900 0.003032 -2.605 0.0104 *
sweep.prod 1.885969 0.839433 2.247 0.0265 *
m_a2 -0.012981 0.006966 -1.863 0.0649 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.238 on 119 degrees of freedom
Multiple R-squared: 0.1293, Adjusted R-squared: 0.1073
F-statistic: 5.888 on 3 and 119 DF, p-value: 0.0008794
|
Call:
lm(formula = y ~ SWV + density + sweep.prod + m_ovality, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.4305 -1.1562 -0.0191 0.9019 7.1817
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 2.032e+01 3.949e+00 5.147 1.23e-06 ***
SWV -1.813e-03 7.203e-04 -2.517 0.0134 *
density -1.063e-02 2.546e-03 -4.176 6.10e-05 ***
sweep.prod 1.206e+00 7.035e-01 1.715 0.0893 .
m_ovality -3.550e+02 2.412e+02 -1.472 0.1441
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.728 on 106 degrees of freedom
Multiple R-squared: 0.231, Adjusted R-squared: 0.202
F-statistic: 7.961 on 4 and 106 DF, p-value: 1.19e-05
|
Call:
lm(formula = y ~ SWV + m_volume + weight, data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.8585 -2.2262 -0.9317 1.9024 14.3969
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 13.692827 4.710130 2.907 0.004371 **
SWV -0.002810 0.001344 -2.091 0.038756 *
m_volume 40.881127 10.858042 3.765 0.000263 ***
weight -0.036638 0.010143 -3.612 0.000450 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.388 on 116 degrees of freedom
Multiple R-squared: 0.1348, Adjusted R-squared: 0.1124
F-statistic: 6.026 on 3 and 116 DF, p-value: 0.0007514
|
Call:
lm(formula = y ~ SWV + density + m_led, data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.0202 -2.3430 -0.7896 1.6908 9.9622
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 25.464085 6.679669 3.812 0.000234 ***
SWV -0.003110 0.001245 -2.498 0.014057 *
density -0.013907 0.004337 -3.207 0.001784 **
m_led 0.009205 0.004313 2.135 0.035147 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.015 on 104 degrees of freedom
Multiple R-squared: 0.158, Adjusted R-squared: 0.1337
F-statistic: 6.504 on 3 and 104 DF, p-value: 0.0004466
|
Call:
lm(formula = y ~ SWV + m_led, data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.0260 -1.6590 -0.2693 1.2890 10.3030
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 17.896113 4.321842 4.141 7.05e-05 ***
SWV -0.003170 0.001128 -2.809 0.00593 **
m_led -0.008465 0.003714 -2.280 0.02467 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.638 on 104 degrees of freedom
Multiple R-squared: 0.08801, Adjusted R-squared: 0.07047
F-statistic: 5.018 on 2 and 104 DF, p-value: 0.008308
|
Call:
lm(formula = y ~ SWV + m_waist, data = LL)
Residuals:
Min 1Q Median 3Q Max
-4.117 -1.458 -0.410 1.079 10.302
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 13.8823417 3.0823416 4.504 1.95e-05 ***
SWV -0.0029211 0.0009381 -3.114 0.00246 **
m_waist -1.1009265 0.6672926 -1.650 0.10239
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.211 on 92 degrees of freedom
Multiple R-squared: 0.1247, Adjusted R-squared: 0.1057
F-statistic: 6.552 on 2 and 92 DF, p-value: 0.002186
|
Call:
lm(formula = y ~ SWV + density + m_taper, data = LL)
Residuals:
Min 1Q Median 3Q Max
-8.0477 -2.3025 -0.5719 1.8777 16.4729
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 50.130387 7.768906 6.453 2.48e-09 ***
SWV -0.006338 0.001486 -4.265 4.04e-05 ***
density -0.016751 0.005007 -3.345 0.00110 **
m_taper -0.344437 0.128428 -2.682 0.00836 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.637 on 119 degrees of freedom
Multiple R-squared: 0.1857, Adjusted R-squared: 0.1651
F-statistic: 9.044 on 3 and 119 DF, p-value: 1.925e-05
|
Call:
lm(formula = y ~ SWV + m_taper + density, data = LL)
Residuals:
Min 1Q Median 3Q Max
-7.9845 -2.2948 -0.4606 1.9663 10.3078
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 48.551065 7.570629 6.413 3.96e-09 ***
SWV -0.006247 0.001435 -4.352 3.10e-05 ***
m_taper -0.397326 0.124624 -3.188 0.00188 **
density -0.015006 0.004846 -3.096 0.00250 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.399 on 107 degrees of freedom
Multiple R-squared: 0.2081, Adjusted R-squared: 0.1859
F-statistic: 9.374 on 3 and 107 DF, p-value: 1.484e-05
|
Call:
lm(formula = y ~ SWV + m_ovality + density + m_taper + m_a2 +
m_a1, data = LL)
Residuals:
Min 1Q Median 3Q Max
-9.588 -3.326 -0.567 2.560 17.202
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 5.375e+01 1.099e+01 4.891 3.35e-06 ***
SWV -8.798e-03 2.102e-03 -4.186 5.65e-05 ***
m_ovality 1.686e+03 6.535e+02 2.580 0.01116 *
density -1.189e-02 6.972e-03 -1.706 0.09078 .
m_taper -5.683e+00 1.801e+00 -3.155 0.00205 **
m_a2 1.152e+00 3.796e-01 3.035 0.00299 **
m_a1 1.124e+00 3.784e-01 2.971 0.00363 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 5.035 on 113 degrees of freedom
Multiple R-squared: 0.2349, Adjusted R-squared: 0.1943
F-statistic: 5.782 on 6 and 113 DF, p-value: 2.798e-05
|
Call:
lm(formula = y ~ SWV + m_taper + density, data = LL)
Residuals:
Min 1Q Median 3Q Max
-9.940 -3.403 -1.019 2.381 18.284
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 51.382178 11.420289 4.499 1.78e-05 ***
SWV -0.008108 0.002159 -3.756 0.000285 ***
m_taper -0.327377 0.189276 -1.730 0.086664 .
density -0.011032 0.007287 -1.514 0.133050
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 5.095 on 104 degrees of freedom
Multiple R-squared: 0.125, Adjusted R-squared: 0.09974
F-statistic: 4.952 on 3 and 104 DF, p-value: 0.002973
|
Call:
lm(formula = y ~ SWV + density + m_taper, data = LL)
Residuals:
Min 1Q Median 3Q Max
-10.252 -3.351 -1.038 2.422 29.742
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 79.129663 14.626657 5.410 4.12e-07 ***
SWV -0.010528 0.002726 -3.862 0.000197 ***
density -0.031996 0.009811 -3.261 0.001505 **
m_taper -0.506055 0.223307 -2.266 0.025531 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 6.205 on 103 degrees of freedom
Multiple R-squared: 0.1841, Adjusted R-squared: 0.1603
F-statistic: 7.746 on 3 and 103 DF, p-value: 0.0001026
|
Call:
lm(formula = y ~ SWV + density + m_taper, data = LL)
Residuals:
Min 1Q Median 3Q Max
-10.092 -3.756 -1.261 2.495 30.034
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 76.685764 15.857936 4.836 5.37e-06 ***
SWV -0.010301 0.002924 -3.523 0.00067 ***
density -0.029706 0.010557 -2.814 0.00600 **
m_taper -0.557956 0.239664 -2.328 0.02212 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 6.389 on 91 degrees of freedom
Multiple R-squared: 0.1738, Adjusted R-squared: 0.1465
F-statistic: 6.379 on 3 and 91 DF, p-value: 0.0005678
|
Call:
lm(formula = y ~ SWV + m_led + density + m_sweep1, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.4066 -1.2787 -0.0760 0.9479 4.7106
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 15.4492981 3.6590429 4.222 4.78e-05 ***
SWV -0.0037534 0.0006806 -5.515 2.09e-07 ***
m_led -0.0134794 0.0022060 -6.110 1.32e-08 ***
density 0.0055963 0.0023843 2.347 0.0206 *
m_sweep1 -0.4608379 0.2696113 -1.709 0.0900 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.715 on 118 degrees of freedom
Multiple R-squared: 0.3499, Adjusted R-squared: 0.3278
F-statistic: 15.88 on 4 and 118 DF, p-value: 2.005e-10
|
Call:
lm(formula = y ~ SWV + m_led + density + m_waist, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.4961 -1.2907 -0.0032 0.9639 4.5572
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 12.9667427 3.9250009 3.304 0.0013 **
SWV -0.0033431 0.0007334 -4.558 1.39e-05 ***
m_led -0.0129257 0.0025281 -5.113 1.42e-06 ***
density 0.0061041 0.0025141 2.428 0.0169 *
m_waist -0.8263980 0.5543254 -1.491 0.1390
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.753 on 106 degrees of freedom
Multiple R-squared: 0.3634, Adjusted R-squared: 0.3394
F-statistic: 15.13 on 4 and 106 DF, p-value: 8.167e-10
|
Call:
lm(formula = y ~ SWV + m_led + density + m_a0 + m_sweep1, data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.0033 -1.6639 -0.0643 1.3943 6.1180
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 15.8020819 5.1682682 3.058 0.002766 **
SWV -0.0042191 0.0009682 -4.358 2.84e-05 ***
m_led -0.0582205 0.0171397 -3.397 0.000932 ***
density 0.0120244 0.0032843 3.661 0.000378 ***
m_a0 0.0419754 0.0178312 2.354 0.020237 *
m_sweep1 -0.7225779 0.3724343 -1.940 0.054768 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.363 on 117 degrees of freedom
Multiple R-squared: 0.3614, Adjusted R-squared: 0.3341
F-statistic: 13.24 on 5 and 117 DF, p-value: 3.178e-10
|
Call:
lm(formula = y ~ SWV + m_led + density + m_taper + m_sweep1,
data = LL)
Residuals:
Min 1Q Median 3Q Max
-4.916 -1.708 0.173 1.350 5.956
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 14.138408 5.421189 2.608 0.010434 *
SWV -0.003843 0.001006 -3.820 0.000226 ***
m_led -0.016962 0.003277 -5.175 1.1e-06 ***
density 0.013002 0.003395 3.829 0.000219 ***
m_taper -0.223891 0.091147 -2.456 0.015674 *
m_sweep1 -0.615403 0.396020 -1.554 0.123201
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.352 on 105 degrees of freedom
Multiple R-squared: 0.3894, Adjusted R-squared: 0.3603
F-statistic: 13.39 on 5 and 105 DF, p-value: 4.249e-10
|
rec = L$nboards.complete/L$volume
for (lmeas in log.quality.measures) {
models <- cf.full(lmeas, idx.sub=rec>quantile(rec, 0.8))
}
Call:
lm(formula = y ~ SWV + density + m_volume + m_whorliness + hw.vfrac +
m_waist + m_a2 + weight, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.7188 -0.3894 -0.0142 0.4668 1.6611
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.481e+01 2.507e+00 -5.909 3.64e-08 ***
SWV 5.044e-03 3.339e-04 15.108 < 2e-16 ***
density 8.795e-03 2.283e-03 3.853 0.000194 ***
m_volume 8.452e+00 4.310e+00 1.961 0.052331 .
m_whorliness -9.294e-01 2.709e-01 -3.430 0.000840 ***
hw.vfrac -3.476e+00 1.260e+00 -2.758 0.006782 **
m_waist 1.269e+01 4.630e+00 2.741 0.007107 **
m_a2 -1.329e-01 5.087e-02 -2.613 0.010186 *
weight -6.934e-03 4.161e-03 -1.666 0.098377 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.7937 on 114 degrees of freedom
Multiple R-squared: 0.7588, Adjusted R-squared: 0.7419
F-statistic: 44.84 on 8 and 114 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + density + m_a2 + m_volume + m_sed, data = LL)
Residuals:
Min 1Q Median 3Q Max
-0.54313 -0.28391 -0.03725 0.19775 0.96497
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.924e+01 2.340e+00 -8.225 1.11e-07 ***
SWV 7.105e-03 4.448e-04 15.972 1.81e-12 ***
density 9.090e-03 1.649e-03 5.513 2.56e-05 ***
m_a2 1.726e-02 4.202e-03 4.108 0.000599 ***
m_volume 1.159e+01 4.388e+00 2.641 0.016118 *
m_sed -2.572e-02 1.148e-02 -2.240 0.037236 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.4123 on 19 degrees of freedom
Multiple R-squared: 0.9458, Adjusted R-squared: 0.9315
F-statistic: 66.25 on 5 and 19 DF, p-value: 2.328e-11
|
Call:
lm(formula = y ~ SWV + density + m_volume + m_whorliness + hw.vfrac +
m_waist + m_a2 + weight, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.7188 -0.3894 -0.0142 0.4668 1.6611
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.481e+01 2.507e+00 -5.909 3.64e-08 ***
SWV 5.044e-03 3.339e-04 15.108 < 2e-16 ***
density 8.795e-03 2.283e-03 3.853 0.000194 ***
m_volume 8.452e+00 4.310e+00 1.961 0.052331 .
m_whorliness -9.294e-01 2.709e-01 -3.430 0.000840 ***
hw.vfrac -3.476e+00 1.260e+00 -2.758 0.006782 **
m_waist 1.269e+01 4.630e+00 2.741 0.007107 **
m_a2 -1.329e-01 5.087e-02 -2.613 0.010186 *
weight -6.934e-03 4.161e-03 -1.666 0.098377 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.7937 on 114 degrees of freedom
Multiple R-squared: 0.7588, Adjusted R-squared: 0.7419
F-statistic: 44.84 on 8 and 114 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + density + m_a2 + m_volume + m_sed, data = LL)
Residuals:
Min 1Q Median 3Q Max
-0.54313 -0.28391 -0.03725 0.19775 0.96497
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.924e+01 2.340e+00 -8.225 1.11e-07 ***
SWV 7.105e-03 4.448e-04 15.972 1.81e-12 ***
density 9.090e-03 1.649e-03 5.513 2.56e-05 ***
m_a2 1.726e-02 4.202e-03 4.108 0.000599 ***
m_volume 1.159e+01 4.388e+00 2.641 0.016118 *
m_sed -2.572e-02 1.148e-02 -2.240 0.037236 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.4123 on 19 degrees of freedom
Multiple R-squared: 0.9458, Adjusted R-squared: 0.9315
F-statistic: 66.25 on 5 and 19 DF, p-value: 2.328e-11
|
Call:
lm(formula = y ~ SWV + density + m_a0 + m_whorliness, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.1729 -0.5000 -0.1065 0.6968 3.3610
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.192e+01 2.354e+00 -5.063 1.60e-06 ***
SWV 3.599e-03 4.353e-04 8.268 2.82e-13 ***
density 1.150e-02 1.530e-03 7.513 1.41e-11 ***
m_a0 -5.816e-03 1.587e-03 -3.665 0.000377 ***
m_whorliness -1.122e+00 3.675e-01 -3.054 0.002809 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.072 on 114 degrees of freedom
Multiple R-squared: 0.5955, Adjusted R-squared: 0.5813
F-statistic: 41.96 on 4 and 114 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + hw.vfrac + m_a0 + m_volume + density,
data = LL)
Residuals:
Min 1Q Median 3Q Max
-0.91656 -0.34733 -0.04219 0.31480 0.82119
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.7131215 4.1012052 -0.418 0.680841
SWV 0.0040847 0.0005567 7.337 5.91e-07 ***
hw.vfrac -5.0581109 2.5973034 -1.947 0.066414 .
m_a0 -0.0636203 0.0138105 -4.607 0.000193 ***
m_volume 22.4440045 5.2038101 4.313 0.000375 ***
density 0.0089556 0.0033116 2.704 0.014058 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.5285 on 19 degrees of freedom
Multiple R-squared: 0.8812, Adjusted R-squared: 0.8499
F-statistic: 28.18 on 5 and 19 DF, p-value: 3.641e-08
|
Call:
lm(formula = y ~ SWV + hw.vfrac + sweep.prod + m_a1 + m_ovality,
data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.4250 -0.7854 0.0482 0.7849 3.4290
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -7.766e+00 1.927e+00 -4.031 0.00011 ***
SWV 6.280e-03 5.832e-04 10.768 < 2e-16 ***
hw.vfrac -7.427e+00 1.351e+00 -5.499 3.04e-07 ***
sweep.prod -1.545e+00 5.176e-01 -2.984 0.00359 **
m_a1 -1.233e-02 4.302e-03 -2.865 0.00510 **
m_ovality 3.087e+02 1.710e+02 1.805 0.07412 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.287 on 98 degrees of freedom
Multiple R-squared: 0.6554, Adjusted R-squared: 0.6379
F-statistic: 37.28 on 5 and 98 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + m_waist + m_sed + m_a2 + weight + sweep.prod +
m_ovality + m_led + hw.vfrac + m_taper, data = LL)
Residuals:
Min 1Q Median 3Q Max
-1.0750 -0.4239 0.1444 0.2693 0.8097
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -3.076e+01 3.618e+00 -8.502 1.14e-06 ***
SWV 8.936e-03 7.622e-04 11.724 2.76e-08 ***
m_waist 1.672e+01 9.097e+00 1.838 0.088954 .
m_sed -7.129e-02 2.816e-02 -2.531 0.025075 *
m_a2 -1.812e-01 1.009e-01 -1.796 0.095739 .
weight -2.836e-02 8.900e-03 -3.187 0.007147 **
sweep.prod -2.458e+00 6.785e-01 -3.622 0.003099 **
m_ovality 4.089e+02 2.158e+02 1.895 0.080590 .
m_led 1.584e-01 3.116e-02 5.084 0.000210 ***
hw.vfrac -1.175e+01 3.797e+00 -3.096 0.008514 **
m_taper -6.774e-01 1.384e-01 -4.895 0.000293 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.5736 on 13 degrees of freedom
Multiple R-squared: 0.9652, Adjusted R-squared: 0.9385
F-statistic: 36.07 on 10 and 13 DF, p-value: 7.747e-08
|
Call:
lm(formula = y ~ SWV + m_a0 + weight + sweep.prod + m_ovality +
m_waist + m_whorliness + hw.vfrac + m_volume, data = LL)
Residuals:
Min 1Q Median 3Q Max
-0.30929 -0.07260 -0.01550 0.07418 0.46518
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.593e+00 2.730e-01 5.835 8.17e-08 ***
SWV -1.022e-04 6.432e-05 -1.589 0.11554
m_a0 -2.873e-03 1.498e-03 -1.918 0.05826 .
weight 1.824e-03 6.152e-04 2.965 0.00386 **
sweep.prod 1.494e-01 5.605e-02 2.666 0.00909 **
m_ovality -4.085e+01 1.764e+01 -2.315 0.02283 *
m_waist -9.980e-02 4.626e-02 -2.157 0.03363 *
m_whorliness -1.013e-01 5.049e-02 -2.006 0.04784 *
hw.vfrac 4.014e-01 1.986e-01 2.022 0.04615 *
m_volume -9.624e-01 6.685e-01 -1.440 0.15342
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.1306 on 91 degrees of freedom
Multiple R-squared: 0.3267, Adjusted R-squared: 0.2601
F-statistic: 4.906 on 9 and 91 DF, p-value: 2.309e-05
|
Call:
lm(formula = y ~ SWV + m_a1 + m_led + weight + m_a2 + m_waist,
data = LL)
Residuals:
Min 1Q Median 3Q Max
-0.120950 -0.059044 0.007078 0.049744 0.109687
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 3.450e+00 4.638e-01 7.438 9.69e-07 ***
SWV -3.106e-04 8.834e-05 -3.516 0.002648 **
m_a1 1.011e-02 2.230e-03 4.536 0.000292 ***
m_led -9.221e-03 1.798e-03 -5.129 8.37e-05 ***
weight 2.791e-03 6.030e-04 4.629 0.000240 ***
m_a2 3.391e-02 1.381e-02 2.455 0.025164 *
m_waist -2.277e+00 1.167e+00 -1.951 0.067693 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.07677 on 17 degrees of freedom
Multiple R-squared: 0.7602, Adjusted R-squared: 0.6755
F-statistic: 8.982 on 6 and 17 DF, p-value: 0.000165
|
Call:
lm(formula = y ~ density + sweep.prod + m_a2, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.4455 -1.4960 -0.3582 0.9658 10.4465
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 11.763314 2.899084 4.058 8.9e-05 ***
density -0.007900 0.003032 -2.605 0.0104 *
sweep.prod 1.885969 0.839433 2.247 0.0265 *
m_a2 -0.012981 0.006966 -1.863 0.0649 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.238 on 119 degrees of freedom
Multiple R-squared: 0.1293, Adjusted R-squared: 0.1073
F-statistic: 5.888 on 3 and 119 DF, p-value: 0.0008794
|
Call:
lm(formula = y ~ 1, data = LL)
Residuals:
Min 1Q Median 3Q Max
-2.7292 -1.8292 -0.3007 0.7708 11.8958
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 4.7292 0.5789 8.17 2.17e-08 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.894 on 24 degrees of freedom
|
Call:
lm(formula = y ~ SWV + m_volume + weight, data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.8585 -2.2262 -0.9317 1.9024 14.3969
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 13.692827 4.710130 2.907 0.004371 **
SWV -0.002810 0.001344 -2.091 0.038756 *
m_volume 40.881127 10.858042 3.765 0.000263 ***
weight -0.036638 0.010143 -3.612 0.000450 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.388 on 116 degrees of freedom
Multiple R-squared: 0.1348, Adjusted R-squared: 0.1124
F-statistic: 6.026 on 3 and 116 DF, p-value: 0.0007514
|
Call:
lm(formula = y ~ m_volume + weight + m_taper, data = LL)
Residuals:
Min 1Q Median 3Q Max
-4.783 -1.768 -1.092 1.315 13.085
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 2.80786 2.65177 1.059 0.30169
m_volume 84.62191 29.75933 2.844 0.00973 **
weight -0.06472 0.02624 -2.466 0.02234 *
m_taper -0.45353 0.32808 -1.382 0.18139
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.612 on 21 degrees of freedom
Multiple R-squared: 0.3839, Adjusted R-squared: 0.2959
F-statistic: 4.361 on 3 and 21 DF, p-value: 0.01547
|
Call:
lm(formula = y ~ SWV + m_led, data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.0260 -1.6590 -0.2693 1.2890 10.3030
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 17.896113 4.321842 4.141 7.05e-05 ***
SWV -0.003170 0.001128 -2.809 0.00593 **
m_led -0.008465 0.003714 -2.280 0.02467 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.638 on 104 degrees of freedom
Multiple R-squared: 0.08801, Adjusted R-squared: 0.07047
F-statistic: 5.018 on 2 and 104 DF, p-value: 0.008308
|
Call:
lm(formula = y ~ m_sweep2, data = LL)
Residuals:
Min 1Q Median 3Q Max
-2.3294 -1.2981 -0.4824 0.3919 5.1041
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 3.427 0.825 4.154 0.000414 ***
m_sweep2 4.677 3.104 1.506 0.146166
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.023 on 22 degrees of freedom
Multiple R-squared: 0.09351, Adjusted R-squared: 0.05231
F-statistic: 2.27 on 1 and 22 DF, p-value: 0.1462
|
Call:
lm(formula = y ~ SWV + density + m_taper, data = LL)
Residuals:
Min 1Q Median 3Q Max
-8.0477 -2.3025 -0.5719 1.8777 16.4729
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 50.130387 7.768906 6.453 2.48e-09 ***
SWV -0.006338 0.001486 -4.265 4.04e-05 ***
density -0.016751 0.005007 -3.345 0.00110 **
m_taper -0.344437 0.128428 -2.682 0.00836 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.637 on 119 degrees of freedom
Multiple R-squared: 0.1857, Adjusted R-squared: 0.1651
F-statistic: 9.044 on 3 and 119 DF, p-value: 1.925e-05
|
Call:
lm(formula = y ~ SWV + weight, data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.9225 -1.2890 -0.0818 1.2802 6.4691
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 49.658489 10.611518 4.680 0.000115 ***
SWV -0.010896 0.002933 -3.715 0.001204 **
weight -0.007575 0.003606 -2.101 0.047341 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.772 on 22 degrees of freedom
Multiple R-squared: 0.387, Adjusted R-squared: 0.3312
F-statistic: 6.943 on 2 and 22 DF, p-value: 0.004597
|
Call:
lm(formula = y ~ SWV + m_ovality + density + m_taper + m_a2 +
m_a1, data = LL)
Residuals:
Min 1Q Median 3Q Max
-9.588 -3.326 -0.567 2.560 17.202
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 5.375e+01 1.099e+01 4.891 3.35e-06 ***
SWV -8.798e-03 2.102e-03 -4.186 5.65e-05 ***
m_ovality 1.686e+03 6.535e+02 2.580 0.01116 *
density -1.189e-02 6.972e-03 -1.706 0.09078 .
m_taper -5.683e+00 1.801e+00 -3.155 0.00205 **
m_a2 1.152e+00 3.796e-01 3.035 0.00299 **
m_a1 1.124e+00 3.784e-01 2.971 0.00363 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 5.035 on 113 degrees of freedom
Multiple R-squared: 0.2349, Adjusted R-squared: 0.1943
F-statistic: 5.782 on 6 and 113 DF, p-value: 2.798e-05
|
Call:
lm(formula = y ~ SWV + weight, data = LL)
Residuals:
Min 1Q Median 3Q Max
-7.4272 -2.4475 0.3669 2.5876 9.4585
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 63.664241 17.805276 3.576 0.00169 **
SWV -0.014296 0.004921 -2.905 0.00820 **
weight -0.012054 0.006050 -1.992 0.05888 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 4.651 on 22 degrees of freedom
Multiple R-squared: 0.2785, Adjusted R-squared: 0.2129
F-statistic: 4.246 on 2 and 22 DF, p-value: 0.02758
|
Call:
lm(formula = y ~ SWV + density + m_taper, data = LL)
Residuals:
Min 1Q Median 3Q Max
-10.252 -3.351 -1.038 2.422 29.742
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 79.129663 14.626657 5.410 4.12e-07 ***
SWV -0.010528 0.002726 -3.862 0.000197 ***
density -0.031996 0.009811 -3.261 0.001505 **
m_taper -0.506055 0.223307 -2.266 0.025531 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 6.205 on 103 degrees of freedom
Multiple R-squared: 0.1841, Adjusted R-squared: 0.1603
F-statistic: 7.746 on 3 and 103 DF, p-value: 0.0001026
|
Call:
lm(formula = y ~ SWV + m_sweep1 + m_whorliness + m_waist + m_a2 +
m_taper, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.9181 -1.5271 0.0877 1.1902 5.2000
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 5.254e+01 9.419e+00 5.578 3.33e-05 ***
SWV -1.203e-02 2.447e-03 -4.916 0.000131 ***
m_sweep1 2.741e+00 9.456e-01 2.899 0.009986 **
m_whorliness -5.276e+00 3.207e+00 -1.645 0.118305
m_waist -1.255e+02 3.483e+01 -3.603 0.002194 **
m_a2 1.333e+00 3.872e-01 3.443 0.003102 **
m_taper -5.297e-01 2.403e-01 -2.204 0.041581 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.452 on 17 degrees of freedom
Multiple R-squared: 0.7567, Adjusted R-squared: 0.6708
F-statistic: 8.813 on 6 and 17 DF, p-value: 0.000185
|
Call:
lm(formula = y ~ SWV + m_led + density + m_sweep1, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.4066 -1.2787 -0.0760 0.9479 4.7106
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 15.4492981 3.6590429 4.222 4.78e-05 ***
SWV -0.0037534 0.0006806 -5.515 2.09e-07 ***
m_led -0.0134794 0.0022060 -6.110 1.32e-08 ***
density 0.0055963 0.0023843 2.347 0.0206 *
m_sweep1 -0.4608379 0.2696113 -1.709 0.0900 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.715 on 118 degrees of freedom
Multiple R-squared: 0.3499, Adjusted R-squared: 0.3278
F-statistic: 15.88 on 4 and 118 DF, p-value: 2.005e-10
|
Call:
lm(formula = y ~ SWV + m_volume + m_sed + weight, data = LL)
Residuals:
Min 1Q Median 3Q Max
-2.6629 -0.5437 0.0701 0.5361 1.7949
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 8.378129 5.832282 1.437 0.166317
SWV -0.004434 0.001188 -3.733 0.001313 **
m_volume -58.040194 12.041565 -4.820 0.000104 ***
m_sed 0.077367 0.029462 2.626 0.016191 *
weight 0.021395 0.008763 2.441 0.024051 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.111 on 20 degrees of freedom
Multiple R-squared: 0.6496, Adjusted R-squared: 0.5795
F-statistic: 9.27 on 4 and 20 DF, p-value: 0.0002091
|
Call:
lm(formula = y ~ SWV + m_led + density + m_a0 + m_sweep1, data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.0033 -1.6639 -0.0643 1.3943 6.1180
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 15.8020819 5.1682682 3.058 0.002766 **
SWV -0.0042191 0.0009682 -4.358 2.84e-05 ***
m_led -0.0582205 0.0171397 -3.397 0.000932 ***
density 0.0120244 0.0032843 3.661 0.000378 ***
m_a0 0.0419754 0.0178312 2.354 0.020237 *
m_sweep1 -0.7225779 0.3724343 -1.940 0.054768 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.363 on 117 degrees of freedom
Multiple R-squared: 0.3614, Adjusted R-squared: 0.3341
F-statistic: 13.24 on 5 and 117 DF, p-value: 3.178e-10
|
Call:
lm(formula = y ~ SWV + m_volume + m_sed + weight + m_whorliness,
data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.2697 -0.8066 -0.1817 0.4722 4.0812
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.314e+01 1.073e+01 1.225 0.235540
SWV -7.987e-03 2.044e-03 -3.908 0.000946 ***
m_volume -1.040e+02 1.992e+01 -5.221 4.86e-05 ***
m_sed 1.643e-01 4.913e-02 3.345 0.003400 **
weight 2.853e-02 1.445e-02 1.975 0.063015 .
m_whorliness -3.948e+00 2.254e+00 -1.752 0.095980 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.832 on 19 degrees of freedom
Multiple R-squared: 0.6946, Adjusted R-squared: 0.6142
F-statistic: 8.643 on 5 and 19 DF, p-value: 0.0002084
|
xyplot(rec ~ volume, L, group=SWILogNumber%in%near.complete.sawpatterns)
for (lmeas in log.quality.measures) {
models <- cf.full(lmeas, idx.sub=L$SWILogNumber%in%near.complete.sawpatterns)
}
Call:
lm(formula = y ~ SWV + density + m_volume + m_whorliness + hw.vfrac +
m_waist + m_a2 + weight, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.7188 -0.3894 -0.0142 0.4668 1.6611
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.481e+01 2.507e+00 -5.909 3.64e-08 ***
SWV 5.044e-03 3.339e-04 15.108 < 2e-16 ***
density 8.795e-03 2.283e-03 3.853 0.000194 ***
m_volume 8.452e+00 4.310e+00 1.961 0.052331 .
m_whorliness -9.294e-01 2.709e-01 -3.430 0.000840 ***
hw.vfrac -3.476e+00 1.260e+00 -2.758 0.006782 **
m_waist 1.269e+01 4.630e+00 2.741 0.007107 **
m_a2 -1.329e-01 5.087e-02 -2.613 0.010186 *
weight -6.934e-03 4.161e-03 -1.666 0.098377 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.7937 on 114 degrees of freedom
Multiple R-squared: 0.7588, Adjusted R-squared: 0.7419
F-statistic: 44.84 on 8 and 114 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + density + m_volume + m_a0, data = LL)
Residuals:
Min 1Q Median 3Q Max
-0.78172 -0.07531 0.02873 0.12207 0.44726
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -2.127e+01 2.260e+00 -9.411 6.35e-08 ***
SWV 6.508e-03 4.077e-04 15.962 3.00e-11 ***
density 1.294e-02 1.552e-03 8.338 3.23e-07 ***
m_volume 8.942e+00 2.536e+00 3.526 0.00281 **
m_a0 -2.127e-02 7.121e-03 -2.986 0.00872 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.3081 on 16 degrees of freedom
Multiple R-squared: 0.9645, Adjusted R-squared: 0.9556
F-statistic: 108.7 on 4 and 16 DF, p-value: 2.201e-11
|
Call:
lm(formula = y ~ SWV + density + m_volume + m_whorliness + hw.vfrac +
m_waist + m_a2 + weight, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.7188 -0.3894 -0.0142 0.4668 1.6611
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.481e+01 2.507e+00 -5.909 3.64e-08 ***
SWV 5.044e-03 3.339e-04 15.108 < 2e-16 ***
density 8.795e-03 2.283e-03 3.853 0.000194 ***
m_volume 8.452e+00 4.310e+00 1.961 0.052331 .
m_whorliness -9.294e-01 2.709e-01 -3.430 0.000840 ***
hw.vfrac -3.476e+00 1.260e+00 -2.758 0.006782 **
m_waist 1.269e+01 4.630e+00 2.741 0.007107 **
m_a2 -1.329e-01 5.087e-02 -2.613 0.010186 *
weight -6.934e-03 4.161e-03 -1.666 0.098377 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.7937 on 114 degrees of freedom
Multiple R-squared: 0.7588, Adjusted R-squared: 0.7419
F-statistic: 44.84 on 8 and 114 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + density + m_volume + m_a0, data = LL)
Residuals:
Min 1Q Median 3Q Max
-0.78172 -0.07531 0.02873 0.12207 0.44726
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -2.127e+01 2.260e+00 -9.411 6.35e-08 ***
SWV 6.508e-03 4.077e-04 15.962 3.00e-11 ***
density 1.294e-02 1.552e-03 8.338 3.23e-07 ***
m_volume 8.942e+00 2.536e+00 3.526 0.00281 **
m_a0 -2.127e-02 7.121e-03 -2.986 0.00872 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.3081 on 16 degrees of freedom
Multiple R-squared: 0.9645, Adjusted R-squared: 0.9556
F-statistic: 108.7 on 4 and 16 DF, p-value: 2.201e-11
|
Call:
lm(formula = y ~ SWV + density + m_a0 + m_whorliness, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.1729 -0.5000 -0.1065 0.6968 3.3610
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -1.192e+01 2.354e+00 -5.063 1.60e-06 ***
SWV 3.599e-03 4.353e-04 8.268 2.82e-13 ***
density 1.150e-02 1.530e-03 7.513 1.41e-11 ***
m_a0 -5.816e-03 1.587e-03 -3.665 0.000377 ***
m_whorliness -1.122e+00 3.675e-01 -3.054 0.002809 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.072 on 114 degrees of freedom
Multiple R-squared: 0.5955, Adjusted R-squared: 0.5813
F-statistic: 41.96 on 4 and 114 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + density + m_sed, data = LL)
Residuals:
Min 1Q Median 3Q Max
-1.0738 -0.5355 -0.3353 0.2977 3.1070
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -13.781815 6.661096 -2.069 0.05410 .
SWV 0.004724 0.001308 3.612 0.00215 **
density 0.009929 0.005129 1.936 0.06971 .
m_sed -0.007942 0.004139 -1.919 0.07196 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.024 on 17 degrees of freedom
Multiple R-squared: 0.7287, Adjusted R-squared: 0.6808
F-statistic: 15.22 on 3 and 17 DF, p-value: 4.565e-05
|
Call:
lm(formula = y ~ SWV + hw.vfrac + sweep.prod + m_a1 + m_ovality,
data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.4250 -0.7854 0.0482 0.7849 3.4290
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -7.766e+00 1.927e+00 -4.031 0.00011 ***
SWV 6.280e-03 5.832e-04 10.768 < 2e-16 ***
hw.vfrac -7.427e+00 1.351e+00 -5.499 3.04e-07 ***
sweep.prod -1.545e+00 5.176e-01 -2.984 0.00359 **
m_a1 -1.233e-02 4.302e-03 -2.865 0.00510 **
m_ovality 3.087e+02 1.710e+02 1.805 0.07412 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.287 on 98 degrees of freedom
Multiple R-squared: 0.6554, Adjusted R-squared: 0.6379
F-statistic: 37.28 on 5 and 98 DF, p-value: < 2.2e-16
|
Call:
lm(formula = y ~ SWV + density + m_ovality + m_taper + m_volume +
m_whorliness + m_sweep1 + m_sed, data = LL)
Residuals:
Min 1Q Median 3Q Max
-0.41403 -0.10908 -0.05871 0.16459 0.46053
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -2.485e+01 2.754e+00 -9.023 4.04e-06 ***
SWV 7.034e-03 4.886e-04 14.395 5.19e-08 ***
density 1.412e-02 1.819e-03 7.758 1.54e-05 ***
m_ovality 3.203e+02 8.540e+01 3.751 0.00378 **
m_taper -8.554e-02 2.615e-02 -3.271 0.00841 **
m_volume 5.671e+00 3.366e+00 1.685 0.12296
m_whorliness 9.803e-01 4.407e-01 2.225 0.05030 .
m_sweep1 -2.341e-01 1.388e-01 -1.687 0.12257
m_sed -1.083e-02 9.454e-03 -1.145 0.27874
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.3186 on 10 degrees of freedom
Multiple R-squared: 0.979, Adjusted R-squared: 0.9622
F-statistic: 58.24 on 8 and 10 DF, p-value: 2.176e-07
|
Call:
lm(formula = y ~ SWV + m_a0 + weight + sweep.prod + m_ovality +
m_waist + m_whorliness + hw.vfrac + m_volume, data = LL)
Residuals:
Min 1Q Median 3Q Max
-0.30929 -0.07260 -0.01550 0.07418 0.46518
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.593e+00 2.730e-01 5.835 8.17e-08 ***
SWV -1.022e-04 6.432e-05 -1.589 0.11554
m_a0 -2.873e-03 1.498e-03 -1.918 0.05826 .
weight 1.824e-03 6.152e-04 2.965 0.00386 **
sweep.prod 1.494e-01 5.605e-02 2.666 0.00909 **
m_ovality -4.085e+01 1.764e+01 -2.315 0.02283 *
m_waist -9.980e-02 4.626e-02 -2.157 0.03363 *
m_whorliness -1.013e-01 5.049e-02 -2.006 0.04784 *
hw.vfrac 4.014e-01 1.986e-01 2.022 0.04615 *
m_volume -9.624e-01 6.685e-01 -1.440 0.15342
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.1306 on 91 degrees of freedom
Multiple R-squared: 0.3267, Adjusted R-squared: 0.2601
F-statistic: 4.906 on 9 and 91 DF, p-value: 2.309e-05
|
Call:
lm(formula = y ~ m_sed + m_led + m_whorliness + m_ovality, data = LL)
Residuals:
Min 1Q Median 3Q Max
-0.12704 -0.06181 -0.01597 0.02134 0.39896
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.177060 0.183065 6.430 1.57e-05 ***
m_sed -0.006065 0.002268 -2.674 0.0181 *
m_led 0.005024 0.002096 2.397 0.0311 *
m_whorliness -0.281484 0.163617 -1.720 0.1074
m_ovality -55.147196 34.460991 -1.600 0.1319
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.1313 on 14 degrees of freedom
Multiple R-squared: 0.4634, Adjusted R-squared: 0.3101
F-statistic: 3.022 on 4 and 14 DF, p-value: 0.05437
|
Call:
lm(formula = y ~ density + sweep.prod + m_a2, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.4455 -1.4960 -0.3582 0.9658 10.4465
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 11.763314 2.899084 4.058 8.9e-05 ***
density -0.007900 0.003032 -2.605 0.0104 *
sweep.prod 1.885969 0.839433 2.247 0.0265 *
m_a2 -0.012981 0.006966 -1.863 0.0649 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.238 on 119 degrees of freedom
Multiple R-squared: 0.1293, Adjusted R-squared: 0.1073
F-statistic: 5.888 on 3 and 119 DF, p-value: 0.0008794
|
Call:
lm(formula = y ~ m_a2, data = LL)
Residuals:
Min 1Q Median 3Q Max
-2.9373 -1.2453 -0.7863 0.8503 10.0570
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 5.51987 0.65140 8.474 7.06e-08 ***
m_a2 -0.03430 0.02247 -1.527 0.143
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.88 on 19 degrees of freedom
Multiple R-squared: 0.1093, Adjusted R-squared: 0.06238
F-statistic: 2.331 on 1 and 19 DF, p-value: 0.1433
|
Call:
lm(formula = y ~ SWV + m_volume + weight, data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.8585 -2.2262 -0.9317 1.9024 14.3969
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 13.692827 4.710130 2.907 0.004371 **
SWV -0.002810 0.001344 -2.091 0.038756 *
m_volume 40.881127 10.858042 3.765 0.000263 ***
weight -0.036638 0.010143 -3.612 0.000450 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.388 on 116 degrees of freedom
Multiple R-squared: 0.1348, Adjusted R-squared: 0.1124
F-statistic: 6.026 on 3 and 116 DF, p-value: 0.0007514
|
Call:
lm(formula = y ~ 1, data = LL)
Residuals:
Min 1Q Median 3Q Max
-4.6944 -2.4611 -0.2111 1.0389 13.3056
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 6.2944 0.8281 7.601 2.55e-07 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.795 on 20 degrees of freedom
|
Call:
lm(formula = y ~ SWV + m_led, data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.0260 -1.6590 -0.2693 1.2890 10.3030
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 17.896113 4.321842 4.141 7.05e-05 ***
SWV -0.003170 0.001128 -2.809 0.00593 **
m_led -0.008465 0.003714 -2.280 0.02467 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.638 on 104 degrees of freedom
Multiple R-squared: 0.08801, Adjusted R-squared: 0.07047
F-statistic: 5.018 on 2 and 104 DF, p-value: 0.008308
|
Call:
lm(formula = y ~ SWV + m_a0 + m_volume + m_whorliness, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.2738 -1.6591 0.2471 1.1572 3.8664
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 58.121087 16.530287 3.516 0.00312 **
SWV -0.006592 0.003289 -2.004 0.06349 .
m_a0 -0.147480 0.055683 -2.649 0.01824 *
m_volume 44.246864 19.849162 2.229 0.04152 *
m_whorliness -5.734834 3.022591 -1.897 0.07721 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.388 on 15 degrees of freedom
Multiple R-squared: 0.4737, Adjusted R-squared: 0.3333
F-statistic: 3.375 on 4 and 15 DF, p-value: 0.03694
|
Call:
lm(formula = y ~ SWV + density + m_taper, data = LL)
Residuals:
Min 1Q Median 3Q Max
-8.0477 -2.3025 -0.5719 1.8777 16.4729
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 50.130387 7.768906 6.453 2.48e-09 ***
SWV -0.006338 0.001486 -4.265 4.04e-05 ***
density -0.016751 0.005007 -3.345 0.00110 **
m_taper -0.344437 0.128428 -2.682 0.00836 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 3.637 on 119 degrees of freedom
Multiple R-squared: 0.1857, Adjusted R-squared: 0.1651
F-statistic: 9.044 on 3 and 119 DF, p-value: 1.925e-05
|
Call:
lm(formula = y ~ SWV + m_led + m_a1, data = LL)
Residuals:
Min 1Q Median 3Q Max
-4.998 -1.306 -0.468 2.124 4.368
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 85.424160 19.852216 4.303 0.000482 ***
SWV -0.019193 0.004654 -4.124 0.000710 ***
m_led -0.030850 0.013088 -2.357 0.030671 *
m_a1 -0.037591 0.027061 -1.389 0.182732
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.854 on 17 degrees of freedom
Multiple R-squared: 0.5409, Adjusted R-squared: 0.4598
F-statistic: 6.676 on 3 and 17 DF, p-value: 0.003523
|
Call:
lm(formula = y ~ SWV + m_ovality + density + m_taper + m_a2 +
m_a1, data = LL)
Residuals:
Min 1Q Median 3Q Max
-9.588 -3.326 -0.567 2.560 17.202
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 5.375e+01 1.099e+01 4.891 3.35e-06 ***
SWV -8.798e-03 2.102e-03 -4.186 5.65e-05 ***
m_ovality 1.686e+03 6.535e+02 2.580 0.01116 *
density -1.189e-02 6.972e-03 -1.706 0.09078 .
m_taper -5.683e+00 1.801e+00 -3.155 0.00205 **
m_a2 1.152e+00 3.796e-01 3.035 0.00299 **
m_a1 1.124e+00 3.784e-01 2.971 0.00363 **
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 5.035 on 113 degrees of freedom
Multiple R-squared: 0.2349, Adjusted R-squared: 0.1943
F-statistic: 5.782 on 6 and 113 DF, p-value: 2.798e-05
|
Call:
lm(formula = y ~ SWV + m_ovality + m_whorliness + m_taper, data = LL)
Residuals:
Min 1Q Median 3Q Max
-8.6264 -3.4477 0.5074 3.2217 8.9738
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 7.653e+01 2.348e+01 3.259 0.00493 **
SWV -2.095e-02 6.073e-03 -3.450 0.00330 **
m_ovality 2.487e+03 1.402e+03 1.774 0.09516 .
m_whorliness 1.026e+01 6.823e+00 1.504 0.15196
m_taper -5.549e-01 4.160e-01 -1.334 0.20094
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 5.517 on 16 degrees of freedom
Multiple R-squared: 0.5431, Adjusted R-squared: 0.4289
F-statistic: 4.755 on 4 and 16 DF, p-value: 0.01015
|
Call:
lm(formula = y ~ SWV + density + m_taper, data = LL)
Residuals:
Min 1Q Median 3Q Max
-10.252 -3.351 -1.038 2.422 29.742
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 79.129663 14.626657 5.410 4.12e-07 ***
SWV -0.010528 0.002726 -3.862 0.000197 ***
density -0.031996 0.009811 -3.261 0.001505 **
m_taper -0.506055 0.223307 -2.266 0.025531 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 6.205 on 103 degrees of freedom
Multiple R-squared: 0.1841, Adjusted R-squared: 0.1603
F-statistic: 7.746 on 3 and 103 DF, p-value: 0.0001026
|
Call:
lm(formula = y ~ SWV + m_a0 + m_whorliness + m_volume + m_a1 +
m_ovality, data = LL)
Residuals:
Min 1Q Median 3Q Max
-6.9359 -2.5266 -0.0042 2.4552 9.4142
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 2.323e+02 4.865e+01 4.774 0.000363 ***
SWV -3.532e-02 9.040e-03 -3.907 0.001802 **
m_a0 -4.652e-01 1.356e-01 -3.431 0.004466 **
m_whorliness -1.779e+01 6.605e+00 -2.693 0.018431 *
m_volume 1.329e+02 4.595e+01 2.892 0.012603 *
m_a1 -8.754e-02 5.657e-02 -1.547 0.145766
m_ovality -1.721e+03 1.343e+03 -1.281 0.222523
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 5.185 on 13 degrees of freedom
Multiple R-squared: 0.6826, Adjusted R-squared: 0.5361
F-statistic: 4.66 on 6 and 13 DF, p-value: 0.009669
|
Call:
lm(formula = y ~ SWV + m_led + density + m_sweep1, data = LL)
Residuals:
Min 1Q Median 3Q Max
-3.4066 -1.2787 -0.0760 0.9479 4.7106
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 15.4492981 3.6590429 4.222 4.78e-05 ***
SWV -0.0037534 0.0006806 -5.515 2.09e-07 ***
m_led -0.0134794 0.0022060 -6.110 1.32e-08 ***
density 0.0055963 0.0023843 2.347 0.0206 *
m_sweep1 -0.4608379 0.2696113 -1.709 0.0900 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 1.715 on 118 degrees of freedom
Multiple R-squared: 0.3499, Adjusted R-squared: 0.3278
F-statistic: 15.88 on 4 and 118 DF, p-value: 2.005e-10
|
Call:
lm(formula = y ~ SWV + m_volume + hw.vfrac + m_a0 + m_whorliness +
m_waist + m_sed + m_sweep2 + density + sweep.prod + m_ovality,
data = LL)
Residuals:
Min 1Q Median 3Q Max
-1.22517 -0.18091 0.05231 0.22905 0.80571
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) -7.150396 8.664772 -0.825 0.4306
SWV -0.001603 0.001525 -1.051 0.3205
m_volume -20.807832 7.825540 -2.659 0.0261 *
hw.vfrac -7.508999 3.810176 -1.971 0.0802 .
m_a0 0.121667 0.043562 2.793 0.0210 *
m_whorliness -2.850101 1.158557 -2.460 0.0362 *
m_waist -1.691958 0.697578 -2.425 0.0383 *
m_sed -0.072499 0.047428 -1.529 0.1607
m_sweep2 11.510867 5.641293 2.040 0.0717 .
density 0.011075 0.004949 2.238 0.0520 .
sweep.prod -3.620607 2.198351 -1.647 0.1340
m_ovality 302.192245 204.333071 1.479 0.1733
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.7081 on 9 degrees of freedom
Multiple R-squared: 0.9034, Adjusted R-squared: 0.7854
F-statistic: 7.653 on 11 and 9 DF, p-value: 0.002479
|
Call:
lm(formula = y ~ SWV + m_led + density + m_a0 + m_sweep1, data = LL)
Residuals:
Min 1Q Median 3Q Max
-5.0033 -1.6639 -0.0643 1.3943 6.1180
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 15.8020819 5.1682682 3.058 0.002766 **
SWV -0.0042191 0.0009682 -4.358 2.84e-05 ***
m_led -0.0582205 0.0171397 -3.397 0.000932 ***
density 0.0120244 0.0032843 3.661 0.000378 ***
m_a0 0.0419754 0.0178312 2.354 0.020237 *
m_sweep1 -0.7225779 0.3724343 -1.940 0.054768 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 2.363 on 117 degrees of freedom
Multiple R-squared: 0.3614, Adjusted R-squared: 0.3341
F-statistic: 13.24 on 5 and 117 DF, p-value: 3.178e-10
|
Call:
lm(formula = y ~ SWV + m_led + m_a0 + m_volume + hw.vfrac + m_a1 +
m_taper + m_sed + m_ovality + weight + m_sweep2, data = LL)
Residuals:
Min 1Q Median 3Q Max
-1.0257 -0.2653 0.0567 0.2088 0.8871
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 8.910779 7.124306 1.251 0.242560
SWV -0.004349 0.001520 -2.861 0.018759 *
m_led -0.230182 0.065158 -3.533 0.006387 **
m_a0 0.444609 0.084431 5.266 0.000517 ***
m_volume -44.248323 7.826131 -5.654 0.000312 ***
hw.vfrac -10.502085 3.795079 -2.767 0.021850 *
m_a1 0.025611 0.008233 3.111 0.012506 *
m_taper 0.871711 0.300456 2.901 0.017558 *
m_sed -0.132019 0.046809 -2.820 0.020035 *
m_ovality 444.467901 201.077124 2.210 0.054407 .
weight 0.010705 0.006724 1.592 0.145837
m_sweep2 1.135885 1.126322 1.008 0.339562
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.6891 on 9 degrees of freedom
Multiple R-squared: 0.9535, Adjusted R-squared: 0.8967
F-statistic: 16.78 on 11 and 9 DF, p-value: 0.0001121
|
Best off using a dynamic estimate of board stiffness based on manual hitman velocity and CHH total density, but other measures of board stiffness (including Metriguard CLT) give similar results.
Green log SWV alone very poorly predicts average dry board stiffness.
Distance from pith at LE has limitations as a predictor for average distance from the pith throughout a board.
The saw pattern plots above indicate that there are a lot of boards missing from the dataset. While in routine operation this is ineveitable (and hence an unaviodable if log performance is to be predicted) in a research context this adds extra confusion owing to the boards being missing to different degrees in different logs and the missing boards being clustered (rather than randomly distributed) within individual logs.